Search

Find a vulnerability

Search criteria

    264 vulnerabilities by vllm-project

    CVE-2026-129356 (GCVE-0-2026-129356)

    Vulnerability from nvd – Published: 2026-11-15 01:15 – Updated: 2026-11-16 15:37 X_Open Source
    VLAI
    Title
    vllm-project vllm Common Prefix single_type_kv_cache_manager.py race condition
    Summary
    A vulnerability was found in vllm-project vllm 0.30.0/0.31.0. This vulnerability affects unknown code of the file single_type_kv_cache_manager.py of the component Common Prefix Handler. The manipulation results in race condition. The attack may be performed from remote. Attacks of this nature are highly complex. It is stated that the exploitability is difficult. The exploit has been made public and could be used. Upgrading to version 0.32.0 is able to resolve this issue. The patch is identified as e687a251bb056fa527846633f7a1b0a6c0f42374. You should upgrade the affected component.
    SSVC
    Exploitation: poc Automatable: no Technical Impact: partial
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-11-16 15:12 UTC
    CWE
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: 0.30.0
    Affected: 0.31.0
    Unaffected: 0.32.0
        cpe:2.3:a:vllm-project:vllm:*:*:*:*:*:*:*:*
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-129356",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-11-16T15:12:04.729936Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-11-16T15:37:21.853Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "cpes": [
                "cpe:2.3:a:vllm-project:vllm:*:*:*:*:*:*:*:*"
              ],
              "modules": [
                "Common Prefix Handler"
              ],
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "status": "affected",
                  "version": "0.30.0"
                },
                {
                  "status": "affected",
                  "version": "0.31.0"
                },
                {
                  "status": "unaffected",
                  "version": "0.32.0"
                }
              ]
            }
          ],
          "credits": [
            {
              "lang": "en",
              "type": "reporter",
              "value": "Zyz3366 (VulDB User)"
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "A vulnerability was found in vllm-project vllm 0.30.0/0.31.0. This vulnerability affects unknown code of the file single_type_kv_cache_manager.py of the component Common Prefix Handler. The manipulation results in race condition. The attack may be performed from remote. Attacks of this nature are highly complex. It is stated that the exploitability is difficult. The exploit has been made public and could be used. Upgrading to version 0.32.0 is able to resolve this issue. The patch is identified as e687a251bb056fa527846633f7a1b0a6c0f42374. You should upgrade the affected component."
            }
          ],
          "metrics": [
            {
              "cvssV4_0": {
                "baseScore": 2.3,
                "baseSeverity": "LOW",
                "vectorString": "CVSS:4.0/AV:N/AC:H/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P",
                "version": "4.0"
              }
            },
            {
              "cvssV3_1": {
                "baseScore": 5,
                "baseSeverity": "MEDIUM",
                "vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:L/I:L/A:L/E:P/RL:O/RC:C",
                "version": "3.1"
              }
            },
            {
              "cvssV3_0": {
                "baseScore": 5,
                "baseSeverity": "MEDIUM",
                "vectorString": "CVSS:3.0/AV:N/AC:H/PR:L/UI:N/S:U/C:L/I:L/A:L/E:P/RL:O/RC:C",
                "version": "3.0"
              }
            },
            {
              "cvssV2_0": {
                "baseScore": 4.6,
                "vectorString": "AV:N/AC:H/Au:S/C:P/I:P/A:P/E:POC/RL:OF/RC:C",
                "version": "2.0"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-362",
                  "description": "Race Condition",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-11-15T01:15:24.018Z",
            "orgId": "1af790b2-7ee1-4545-860a-a788eba489b5",
            "shortName": "VulDB"
          },
          "references": [
            {
              "name": "VDB-437419 | vllm-project vllm Common Prefix single_type_kv_cache_manager.py race condition",
              "tags": [
                "vdb-entry"
              ],
              "url": "https://vuldb.com/vuln/437419"
            },
            {
              "name": "VDB-437419 | CTI Indicators (IOB, IOC, IOA)",
              "tags": [
                "signature",
                "permissions-required"
              ],
              "url": "https://vuldb.com/vuln/437419/cti"
            },
            {
              "name": "CVE-2026-129356 | CVE Analysis and Report",
              "tags": [
                "third-party-advisory"
              ],
              "url": "https://vuldb.com/cve/CVE-2026-129356"
            },
            {
              "name": "Submit #1043823 | vLLM Project vLLM v0.30.0, v0.31.0 Improper Resource Management",
              "tags": [
                "third-party-advisory"
              ],
              "url": "https://vuldb.com/submit/1043823"
            },
            {
              "tags": [
                "exploit",
                "issue-tracking"
              ],
              "url": "https://github.com/vllm-project/vllm/issues/61673"
            },
            {
              "tags": [
                "issue-tracking",
                "patch"
              ],
              "url": "https://github.com/vllm-project/vllm/pull/61126"
            },
            {
              "tags": [
                "patch"
              ],
              "url": "https://github.com/vllm-project/vllm/commit/e687a251bb056fa527846633f7a1b0a6c0f42374"
            },
            {
              "tags": [
                "patch"
              ],
              "url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"
            },
            {
              "tags": [
                "product"
              ],
              "url": "https://github.com/vllm-project/vllm/"
            }
          ],
          "tags": [
            "x_open-source"
          ],
          "timeline": [
            {
              "lang": "en",
              "time": "2026-11-14T00:00:00.000Z",
              "value": "Advisory disclosed"
            },
            {
              "lang": "en",
              "time": "2026-11-14T01:00:00.000Z",
              "value": "VulDB entry created"
            },
            {
              "lang": "en",
              "time": "2026-11-14T07:47:52.000Z",
              "value": "VulDB entry last update"
            }
          ],
          "title": "vllm-project vllm Common Prefix single_type_kv_cache_manager.py race condition",
          "x_generator": [
            "VulDB PVTS v202611"
          ]
        }
      },
      "cveMetadata": {
        "assignerOrgId": "1af790b2-7ee1-4545-860a-a788eba489b5",
        "assignerShortName": "VulDB",
        "cveId": "CVE-2026-129356",
        "datePublished": "2026-11-15T01:15:24.018Z",
        "dateReserved": "2026-11-14T06:42:47.336Z",
        "dateUpdated": "2026-11-16T15:37:21.853Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-126399 (GCVE-0-2026-126399)

    Vulnerability from nvd – Published: 2026-11-13 09:35 – Updated: 2026-11-13 15:55
    VLAI
    Title
    vLLM 0.19.0 before 0.31.0 Resource Exhaustion via Request-Level num_frames
    Summary
    vLLM from 0.19.0 before 0.31.0 contains a resource exhaustion vulnerability that allows inference clients to bypass the server frame limit by setting media_io_kwargs.video.num_frames in chat completion requests. Attackers can supply num_frames=-1 or a large value with many base64 JPEG frames, forcing VideoMediaIO to decode all frames and np.stack them, causing memory exhaustion.
    SSVC
    Exploitation: none Automatable: no Technical Impact: partial
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-11-13 15:30 UTC
    CWE
    • CWE-770 - Allocation of Resources Without Limits or Throttling
    References
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: 0.19.0 , < 0.31.0 (semver)
    Unaffected: 0.31.0 (semver)
        cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
    Create a notification for this product.
    Date Public
    2026-10-27 00:00
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-126399",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-11-13T15:30:26.279127Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-11-13T15:55:11.981Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "defaultStatus": "unaffected",
              "packageURL": "pkg:pypi/vllm",
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "lessThan": "0.31.0",
                  "status": "affected",
                  "version": "0.19.0",
                  "versionType": "semver"
                },
                {
                  "status": "unaffected",
                  "version": "0.31.0",
                  "versionType": "semver"
                }
              ]
            }
          ],
          "cpeApplicability": [
            {
              "nodes": [
                {
                  "cpeMatch": [
                    {
                      "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
                      "versionEndExcluding": "0.31.0",
                      "versionStartIncluding": "0.19.0",
                      "vulnerable": true
                    }
                  ],
                  "negate": false,
                  "operator": "OR"
                }
              ]
            }
          ],
          "credits": [
            {
              "lang": "en",
              "type": "reporter",
              "value": "m4rgh"
            },
            {
              "lang": "en",
              "type": "coordinator",
              "value": "jperezdealgaba"
            }
          ],
          "datePublic": "2026-10-27T00:00:00.000Z",
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM from 0.19.0 before 0.31.0 contains a resource exhaustion vulnerability that allows inference clients to bypass the server frame limit by setting media_io_kwargs.video.num_frames in chat completion requests. Attackers can supply num_frames=-1 or a large value with many base64 JPEG frames, forcing VideoMediaIO to decode all frames and np.stack them, causing memory exhaustion."
            }
          ],
          "metrics": [
            {
              "cvssV4_0": {
                "attackComplexity": "LOW",
                "attackRequirements": "NONE",
                "attackVector": "NETWORK",
                "baseScore": 7.1,
                "baseSeverity": "HIGH",
                "privilegesRequired": "LOW",
                "subAvailabilityImpact": "NONE",
                "subConfidentialityImpact": "NONE",
                "subIntegrityImpact": "NONE",
                "userInteraction": "NONE",
                "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N",
                "version": "4.0",
                "vulnAvailabilityImpact": "HIGH",
                "vulnConfidentialityImpact": "NONE",
                "vulnIntegrityImpact": "NONE"
              },
              "format": "CVSS"
            },
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 6.5,
                "baseSeverity": "MEDIUM",
                "confidentialityImpact": "NONE",
                "integrityImpact": "NONE",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
                "version": "3.1"
              },
              "format": "CVSS"
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-770",
                  "description": "Allocation of Resources Without Limits or Throttling",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-11-13T09:35:48.994Z",
            "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
            "shortName": "VulnCheck"
          },
          "references": [
            {
              "name": "GitHub Security Advisory (GHSA-vxqj-p4gw-9h4c)",
              "tags": [
                "vendor-advisory"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-vxqj-p4gw-9h4c"
            },
            {
              "name": "VulnCheck Advisory: vLLM 0.19.0 before 0.31.0 Resource Exhaustion via Request-Level num_frames",
              "tags": [
                "third-party-advisory"
              ],
              "url": "https://www.vulncheck.com/advisories/vllm-0.19.0-before-0.31.0-resource-exhaustion-via-request-level-num-frames"
            }
          ],
          "title": "vLLM 0.19.0 before 0.31.0 Resource Exhaustion via Request-Level num_frames",
          "x_generator": {
            "engine": "vulncheck-endgame"
          }
        }
      },
      "cveMetadata": {
        "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "assignerShortName": "VulnCheck",
        "cveId": "CVE-2026-126399",
        "datePublished": "2026-11-13T09:35:48.994Z",
        "dateReserved": "2026-11-10T21:32:21.764Z",
        "dateUpdated": "2026-11-13T15:55:11.981Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-126398 (GCVE-0-2026-126398)

    Vulnerability from nvd – Published: 2026-11-13 09:35 – Updated: 2026-11-13 09:35
    VLAI
    Title
    vLLM 0.28.0 before 0.30.0 Denial of Service via Prompt Embeds on XD-RoPE Models
    Summary
    vLLM from 0.28.0 before 0.30.0 contains a reachable assertion vulnerability in GPUModelRunner._init_xdrope_positions that allows remote attackers to crash the engine by submitting embeddings-only requests. Attackers can send a /v1/completions request containing only prompt_embeds to XD-RoPE models with --enable-prompt-embeds, terminating the EngineCore and API server for all clients.
    CWE
    References
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: 0.28.0 , < 0.30.0 (semver)
    Unaffected: 0.30.0 (semver)
        cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
    Create a notification for this product.
    Date Public
    2026-10-27 00:00
    Show details on NVD website

    {
      "containers": {
        "cna": {
          "affected": [
            {
              "defaultStatus": "unaffected",
              "packageURL": "pkg:pypi/vllm",
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "lessThan": "0.30.0",
                  "status": "affected",
                  "version": "0.28.0",
                  "versionType": "semver"
                },
                {
                  "status": "unaffected",
                  "version": "0.30.0",
                  "versionType": "semver"
                }
              ]
            }
          ],
          "cpeApplicability": [
            {
              "nodes": [
                {
                  "cpeMatch": [
                    {
                      "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
                      "versionEndExcluding": "0.30.0",
                      "versionStartIncluding": "0.28.0",
                      "vulnerable": true
                    }
                  ],
                  "negate": false,
                  "operator": "OR"
                }
              ]
            }
          ],
          "credits": [
            {
              "lang": "en",
              "type": "reporter",
              "value": "wildoranges"
            },
            {
              "lang": "en",
              "type": "coordinator",
              "value": "jperezdealgaba"
            }
          ],
          "datePublic": "2026-10-27T00:00:00.000Z",
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM from 0.28.0 before 0.30.0 contains a reachable assertion vulnerability in GPUModelRunner._init_xdrope_positions that allows remote attackers to crash the engine by submitting embeddings-only requests. Attackers can send a /v1/completions request containing only prompt_embeds to XD-RoPE models with --enable-prompt-embeds, terminating the EngineCore and API server for all clients."
            }
          ],
          "metrics": [
            {
              "cvssV4_0": {
                "attackComplexity": "HIGH",
                "attackRequirements": "PRESENT",
                "attackVector": "NETWORK",
                "baseScore": 8.2,
                "baseSeverity": "HIGH",
                "privilegesRequired": "NONE",
                "subAvailabilityImpact": "NONE",
                "subConfidentialityImpact": "NONE",
                "subIntegrityImpact": "NONE",
                "userInteraction": "NONE",
                "vectorString": "CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N",
                "version": "4.0",
                "vulnAvailabilityImpact": "HIGH",
                "vulnConfidentialityImpact": "NONE",
                "vulnIntegrityImpact": "NONE"
              },
              "format": "CVSS"
            },
            {
              "cvssV3_1": {
                "attackComplexity": "HIGH",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 5.9,
                "baseSeverity": "MEDIUM",
                "confidentialityImpact": "NONE",
                "integrityImpact": "NONE",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H",
                "version": "3.1"
              },
              "format": "CVSS"
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-617",
                  "description": "Reachable Assertion",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-11-13T09:35:49.601Z",
            "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
            "shortName": "VulnCheck"
          },
          "references": [
            {
              "name": "GitHub Security Advisory (GHSA-5q78-j82c-2vr2)",
              "tags": [
                "vendor-advisory"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-5q78-j82c-2vr2"
            },
            {
              "name": "VulnCheck Advisory: vLLM 0.28.0 before 0.30.0 Denial of Service via Prompt Embeds on XD-RoPE Models",
              "tags": [
                "third-party-advisory"
              ],
              "url": "https://www.vulncheck.com/advisories/vllm-0.28.0-before-0.30.0-denial-of-service-via-prompt-embeds-on-xd-rope-models"
            }
          ],
          "title": "vLLM 0.28.0 before 0.30.0 Denial of Service via Prompt Embeds on XD-RoPE Models",
          "x_generator": {
            "engine": "vulncheck-endgame"
          }
        }
      },
      "cveMetadata": {
        "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "assignerShortName": "VulnCheck",
        "cveId": "CVE-2026-126398",
        "datePublished": "2026-11-13T09:35:49.601Z",
        "dateReserved": "2026-11-10T21:30:16.910Z",
        "dateUpdated": "2026-11-13T09:35:49.601Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-126397 (GCVE-0-2026-126397)

    Vulnerability from nvd – Published: 2026-11-13 09:35 – Updated: 2026-11-13 09:35
    VLAI
    Title
    vLLM 0.10.1 before 0.31.0 Cohere2 Vision DoS via max_patches
    Summary
    vLLM from 0.10.1 before 0.31.0 forwards a request-controlled mm_processor_kwargs.max_patches value to the Hugging Face processor for Cohere2 Vision models without a server-side upper bound, causing quadratic CPU work during multimodal preprocessing. Remote clients can send small image chat-completion requests with large, varying max_patches values to bypass the LRU cache, exhaust preprocessing workers, and deny service to other clients.
    CWE
    • CWE-400 - Uncontrolled Resource Consumption
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: 0.10.1 , < 0.31.0 (semver)
    Unaffected: 0.31.0 (semver)
        cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
    Create a notification for this product.
    Date Public
    2026-10-27 00:00
    Show details on NVD website

    {
      "containers": {
        "cna": {
          "affected": [
            {
              "defaultStatus": "unaffected",
              "packageURL": "pkg:pypi/vllm",
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "lessThan": "0.31.0",
                  "status": "affected",
                  "version": "0.10.1",
                  "versionType": "semver"
                },
                {
                  "status": "unaffected",
                  "version": "0.31.0",
                  "versionType": "semver"
                }
              ]
            }
          ],
          "cpeApplicability": [
            {
              "nodes": [
                {
                  "cpeMatch": [
                    {
                      "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
                      "versionEndExcluding": "0.31.0",
                      "versionStartIncluding": "0.10.1",
                      "vulnerable": true
                    }
                  ],
                  "negate": false,
                  "operator": "OR"
                }
              ]
            }
          ],
          "credits": [
            {
              "lang": "en",
              "type": "reporter",
              "value": "0xbbdd"
            },
            {
              "lang": "en",
              "type": "coordinator",
              "value": "jperezdealgaba"
            }
          ],
          "datePublic": "2026-10-27T00:00:00.000Z",
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM from 0.10.1 before 0.31.0 forwards a request-controlled mm_processor_kwargs.max_patches value to the Hugging Face processor for Cohere2 Vision models without a server-side upper bound, causing quadratic CPU work during multimodal preprocessing. Remote clients can send small image chat-completion requests with large, varying max_patches values to bypass the LRU cache, exhaust preprocessing workers, and deny service to other clients."
            }
          ],
          "metrics": [
            {
              "cvssV4_0": {
                "Automatable": "NOT_DEFINED",
                "Recovery": "NOT_DEFINED",
                "Safety": "NOT_DEFINED",
                "attackComplexity": "LOW",
                "attackRequirements": "NONE",
                "attackVector": "NETWORK",
                "baseScore": 8.7,
                "baseSeverity": "HIGH",
                "exploitMaturity": "NOT_DEFINED",
                "privilegesRequired": "NONE",
                "providerUrgency": "NOT_DEFINED",
                "subAvailabilityImpact": "NONE",
                "subConfidentialityImpact": "NONE",
                "subIntegrityImpact": "NONE",
                "userInteraction": "NONE",
                "valueDensity": "NOT_DEFINED",
                "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N",
                "version": "4.0",
                "vulnAvailabilityImpact": "HIGH",
                "vulnConfidentialityImpact": "NONE",
                "vulnIntegrityImpact": "NONE",
                "vulnerabilityResponseEffort": "NOT_DEFINED"
              },
              "format": "CVSS"
            },
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 7.5,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "NONE",
                "integrityImpact": "NONE",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H",
                "version": "3.1"
              },
              "format": "CVSS"
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-400",
                  "description": "Uncontrolled Resource Consumption",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-11-13T09:35:50.274Z",
            "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
            "shortName": "VulnCheck"
          },
          "references": [
            {
              "name": "GitHub Security Advisory (GHSA-9g3c-x747-c6wr)",
              "tags": [
                "vendor-advisory"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-9g3c-x747-c6wr"
            },
            {
              "name": "Patch Commit",
              "tags": [
                "patch"
              ],
              "url": "https://github.com/vllm-project/vllm/commit/f6326f53bda46898a331c2d24500332c285d9a2b"
            },
            {
              "name": "VulnCheck Advisory: vLLM 0.10.1 before 0.31.0 Cohere2 Vision DoS via max_patches",
              "tags": [
                "third-party-advisory"
              ],
              "url": "https://www.vulncheck.com/advisories/vllm-0.10.1-before-0.31.0-cohere2-vision-dos-via-max-patches"
            }
          ],
          "title": "vLLM 0.10.1 before 0.31.0 Cohere2 Vision DoS via max_patches",
          "x_generator": {
            "engine": "vulncheck-endgame"
          }
        }
      },
      "cveMetadata": {
        "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "assignerShortName": "VulnCheck",
        "cveId": "CVE-2026-126397",
        "datePublished": "2026-11-13T09:35:50.274Z",
        "dateReserved": "2026-11-10T21:30:16.910Z",
        "dateUpdated": "2026-11-13T09:35:50.274Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-126396 (GCVE-0-2026-126396)

    Vulnerability from nvd – Published: 2026-11-13 09:35 – Updated: 2026-11-13 20:27
    VLAI
    Title
    vLLM from 0.24.0 before 0.31.0 Resource Exhaustion via MiniMax M3 min_pixels
    Summary
    vLLM from 0.24.0 before 0.31.0 contains a resource exhaustion vulnerability in the MiniMax M3 VL video processor, which accepts request-level min_pixels without range or min_pixels <= max_pixels validation. Its video-wide pixel budget is enforced only when max_long_side_pixel is set, and that value defaults to None. API clients can supply a large min_pixels via mm_processor_kwargs to enlarge every decoded frame, causing excessive CPU and host-memory consumption that may disrupt workers or the service.
    SSVC
    Exploitation: none Automatable: yes Technical Impact: partial
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-11-13 20:27 UTC
    CWE
    • CWE-770 - Allocation of Resources Without Limits or Throttling
    References
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: 0.24.0 , < 0.31.0 (semver)
    Unaffected: 0.31.0 (semver)
        cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
    Create a notification for this product.
    Date Public
    2026-10-27 00:00
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-126396",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-11-13T20:27:09.832988Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-11-13T20:27:21.640Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "defaultStatus": "unaffected",
              "packageURL": "pkg:pypi/vllm",
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "lessThan": "0.31.0",
                  "status": "affected",
                  "version": "0.24.0",
                  "versionType": "semver"
                },
                {
                  "status": "unaffected",
                  "version": "0.31.0",
                  "versionType": "semver"
                }
              ]
            }
          ],
          "cpeApplicability": [
            {
              "nodes": [
                {
                  "cpeMatch": [
                    {
                      "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
                      "versionEndExcluding": "0.31.0",
                      "versionStartIncluding": "0.24.0",
                      "vulnerable": true
                    }
                  ],
                  "operator": "OR"
                }
              ]
            }
          ],
          "credits": [
            {
              "lang": "en",
              "type": "reporter",
              "value": "mg-princess"
            },
            {
              "lang": "en",
              "type": "coordinator",
              "value": "jperezdealgaba"
            }
          ],
          "datePublic": "2026-10-27T00:00:00.000Z",
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM from 0.24.0 before 0.31.0 contains a resource exhaustion vulnerability in the MiniMax M3 VL video processor, which accepts request-level min_pixels without range or min_pixels \u003c= max_pixels validation. Its video-wide pixel budget is enforced only when max_long_side_pixel is set, and that value defaults to None. API clients can supply a large min_pixels via mm_processor_kwargs to enlarge every decoded frame, causing excessive CPU and host-memory consumption that may disrupt workers or the service."
            }
          ],
          "metrics": [
            {
              "cvssV4_0": {
                "Automatable": "NOT_DEFINED",
                "Recovery": "NOT_DEFINED",
                "Safety": "NOT_DEFINED",
                "attackComplexity": "LOW",
                "attackRequirements": "NONE",
                "attackVector": "NETWORK",
                "baseScore": 6.9,
                "baseSeverity": "MEDIUM",
                "exploitMaturity": "NOT_DEFINED",
                "privilegesRequired": "NONE",
                "providerUrgency": "NOT_DEFINED",
                "subAvailabilityImpact": "NONE",
                "subConfidentialityImpact": "NONE",
                "subIntegrityImpact": "NONE",
                "userInteraction": "NONE",
                "valueDensity": "NOT_DEFINED",
                "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N",
                "version": "4.0",
                "vulnAvailabilityImpact": "LOW",
                "vulnConfidentialityImpact": "NONE",
                "vulnIntegrityImpact": "NONE",
                "vulnerabilityResponseEffort": "NOT_DEFINED"
              },
              "format": "CVSS",
              "scenarios": [
                {
                  "lang": "en",
                  "value": "GENERAL"
                }
              ]
            },
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "LOW",
                "baseScore": 5.3,
                "baseSeverity": "MEDIUM",
                "confidentialityImpact": "NONE",
                "integrityImpact": "NONE",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L",
                "version": "3.1"
              },
              "format": "CVSS",
              "scenarios": [
                {
                  "lang": "en",
                  "value": "GENERAL"
                }
              ]
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-770",
                  "description": "Allocation of Resources Without Limits or Throttling",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-11-13T11:44:37.122Z",
            "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
            "shortName": "VulnCheck"
          },
          "references": [
            {
              "name": "GitHub Security Advisory (GHSA-w4cg-mhc7-mgw3)",
              "tags": [
                "vendor-advisory"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-w4cg-mhc7-mgw3"
            },
            {
              "name": "VulnCheck Advisory: vLLM from 0.24.0 before 0.31.0 Resource Exhaustion via MiniMax M3 min_pixels",
              "tags": [
                "third-party-advisory"
              ],
              "url": "https://www.vulncheck.com/advisories/vllm-from-0.24.0-before-0.31.0-resource-exhaustion-via-minimax-m3-min-pixels"
            }
          ],
          "title": "vLLM from 0.24.0 before 0.31.0 Resource Exhaustion via MiniMax M3 min_pixels",
          "x_generator": {
            "engine": "vulncheck-endgame"
          }
        }
      },
      "cveMetadata": {
        "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "assignerShortName": "VulnCheck",
        "cveId": "CVE-2026-126396",
        "datePublished": "2026-11-13T09:35:50.950Z",
        "dateReserved": "2026-11-10T21:30:16.910Z",
        "dateUpdated": "2026-11-13T20:27:21.640Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-126395 (GCVE-0-2026-126395)

    Vulnerability from nvd – Published: 2026-11-13 09:35 – Updated: 2026-11-13 22:30
    VLAI
    Title
    vLLM 0.14.0rc1 before 0.31.0 Heap Address Disclosure via sanitize_message()
    Summary
    vLLM from 0.14.0rc1 before 0.31.0 contains an information disclosure vulnerability in sanitize_message() whose lowercase-only regex fails to scrub uppercase PIL image addresses. Unauthenticated attackers can send a crafted PNG to endpoints such as /tokenize, triggering HF-processor errors that leak live server heap addresses useful for ASLR bypass.
    SSVC
    Exploitation: none Automatable: yes Technical Impact: partial
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-11-13 16:34 UTC
    CWE
    • CWE-532 - Insertion of Sensitive Information into Log File
    References
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: 0.14.0rc1 , < 0.31.0 (custom)
    Unaffected: 0.31.0 (custom)
        cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
    Create a notification for this product.
    Date Public
    2026-10-27 00:00
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-126395",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-11-13T16:34:31.048655Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-11-13T22:30:11.255Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "defaultStatus": "unaffected",
              "packageURL": "pkg:pypi/vllm",
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "lessThan": "0.31.0",
                  "status": "affected",
                  "version": "0.14.0rc1",
                  "versionType": "custom"
                },
                {
                  "status": "unaffected",
                  "version": "0.31.0",
                  "versionType": "custom"
                }
              ]
            }
          ],
          "cpeApplicability": [
            {
              "nodes": [
                {
                  "cpeMatch": [
                    {
                      "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
                      "versionEndExcluding": "0.31.0",
                      "versionStartIncluding": "0.14.0rc1",
                      "vulnerable": true
                    }
                  ],
                  "negate": false,
                  "operator": "OR"
                }
              ]
            }
          ],
          "credits": [
            {
              "lang": "en",
              "type": "reporter",
              "value": "0xiviel"
            },
            {
              "lang": "en",
              "type": "coordinator",
              "value": "jperezdealgaba"
            },
            {
              "lang": "en",
              "type": "remediation developer",
              "value": "DarkLight1337"
            }
          ],
          "datePublic": "2026-10-27T00:00:00.000Z",
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM from 0.14.0rc1 before 0.31.0 contains an information disclosure vulnerability in sanitize_message() whose lowercase-only regex fails to scrub uppercase PIL image addresses. Unauthenticated attackers can send a crafted PNG to endpoints such as /tokenize, triggering HF-processor errors that leak live server heap addresses useful for ASLR bypass."
            }
          ],
          "metrics": [
            {
              "cvssV4_0": {
                "attackComplexity": "LOW",
                "attackRequirements": "NONE",
                "attackVector": "NETWORK",
                "baseScore": 6.9,
                "baseSeverity": "MEDIUM",
                "privilegesRequired": "NONE",
                "subAvailabilityImpact": "NONE",
                "subConfidentialityImpact": "NONE",
                "subIntegrityImpact": "NONE",
                "userInteraction": "NONE",
                "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:N/VA:N/SC:N/SI:N/SA:N",
                "version": "4.0",
                "vulnAvailabilityImpact": "NONE",
                "vulnConfidentialityImpact": "LOW",
                "vulnIntegrityImpact": "NONE"
              },
              "format": "CVSS"
            },
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "NONE",
                "baseScore": 5.3,
                "baseSeverity": "MEDIUM",
                "confidentialityImpact": "LOW",
                "integrityImpact": "NONE",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N",
                "version": "3.1"
              },
              "format": "CVSS"
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-532",
                  "description": "Insertion of Sensitive Information into Log File",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-11-13T09:35:51.636Z",
            "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
            "shortName": "VulnCheck"
          },
          "references": [
            {
              "name": "GitHub Security Advisory (GHSA-m9fg-w9qh-67pc)",
              "tags": [
                "vendor-advisory"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-m9fg-w9qh-67pc"
            },
            {
              "name": "VulnCheck Advisory: vLLM 0.14.0rc1 before 0.31.0 Heap Address Disclosure via sanitize_message()",
              "tags": [
                "third-party-advisory"
              ],
              "url": "https://www.vulncheck.com/advisories/vllm-0.14-0rc1-before-0.31.0-heap-address-disclosure-via-sanitize-message"
            }
          ],
          "title": "vLLM 0.14.0rc1 before 0.31.0 Heap Address Disclosure via sanitize_message()",
          "x_generator": {
            "engine": "vulncheck-endgame"
          }
        }
      },
      "cveMetadata": {
        "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "assignerShortName": "VulnCheck",
        "cveId": "CVE-2026-126395",
        "datePublished": "2026-11-13T09:35:51.636Z",
        "dateReserved": "2026-11-10T21:30:16.910Z",
        "dateUpdated": "2026-11-13T22:30:11.255Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-126394 (GCVE-0-2026-126394)

    Vulnerability from nvd – Published: 2026-11-13 09:35 – Updated: 2026-11-13 09:35
    VLAI
    Title
    vLLM 0.30.0 before 0.31.0 Resource Exhaustion via OpenPangu Video Backend num_frames
    Summary
    vLLM 0.30.0 before 0.31.0 contains a resource exhaustion vulnerability in OpenCVDynamicOpenPanguVideoBackend, which uses request-controlled num_frames without an effective ceiling. Unauthenticated attackers can send /v1/chat/completions or /tokenize requests selecting the openpangu video_backend with a huge num_frames, forcing np.linspace allocations and CPU work that OOM-kill the API server.
    CWE
    • CWE-770 - Allocation of Resources Without Limits or Throttling
    References
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: 0.30.0 , < 0.31.0 (semver)
    Unaffected: 0.31.0 (semver)
        cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
    Create a notification for this product.
    Date Public
    2026-10-27 00:00
    Show details on NVD website

    {
      "containers": {
        "cna": {
          "affected": [
            {
              "defaultStatus": "unaffected",
              "packageURL": "pkg:pypi/vllm",
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "lessThan": "0.31.0",
                  "status": "affected",
                  "version": "0.30.0",
                  "versionType": "semver"
                },
                {
                  "status": "unaffected",
                  "version": "0.31.0",
                  "versionType": "semver"
                }
              ]
            }
          ],
          "cpeApplicability": [
            {
              "nodes": [
                {
                  "cpeMatch": [
                    {
                      "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
                      "versionEndExcluding": "0.31.0",
                      "versionStartIncluding": "0.30.0",
                      "vulnerable": true
                    }
                  ],
                  "negate": false,
                  "operator": "OR"
                }
              ]
            }
          ],
          "credits": [
            {
              "lang": "en",
              "type": "reporter",
              "value": "gn00295120"
            },
            {
              "lang": "en",
              "type": "coordinator",
              "value": "jperezdealgaba"
            }
          ],
          "datePublic": "2026-10-27T00:00:00.000Z",
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM 0.30.0 before 0.31.0 contains a resource exhaustion vulnerability in OpenCVDynamicOpenPanguVideoBackend, which uses request-controlled num_frames without an effective ceiling. Unauthenticated attackers can send /v1/chat/completions or /tokenize requests selecting the openpangu video_backend with a huge num_frames, forcing np.linspace allocations and CPU work that OOM-kill the API server."
            }
          ],
          "metrics": [
            {
              "cvssV4_0": {
                "attackComplexity": "LOW",
                "attackRequirements": "NONE",
                "attackVector": "NETWORK",
                "baseScore": 6.9,
                "baseSeverity": "MEDIUM",
                "privilegesRequired": "NONE",
                "subAvailabilityImpact": "NONE",
                "subConfidentialityImpact": "NONE",
                "subIntegrityImpact": "NONE",
                "userInteraction": "NONE",
                "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N",
                "version": "4.0",
                "vulnAvailabilityImpact": "LOW",
                "vulnConfidentialityImpact": "NONE",
                "vulnIntegrityImpact": "NONE"
              },
              "format": "CVSS"
            },
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "LOW",
                "baseScore": 5.3,
                "baseSeverity": "MEDIUM",
                "confidentialityImpact": "NONE",
                "integrityImpact": "NONE",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L",
                "version": "3.1"
              },
              "format": "CVSS"
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-770",
                  "description": "Allocation of Resources Without Limits or Throttling",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-11-13T09:35:52.305Z",
            "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
            "shortName": "VulnCheck"
          },
          "references": [
            {
              "name": "GitHub Security Advisory (GHSA-894j-wg8m-63h8)",
              "tags": [
                "vendor-advisory"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-894j-wg8m-63h8"
            },
            {
              "name": "VulnCheck Advisory: vLLM 0.30.0 before 0.31.0 Resource Exhaustion via OpenPangu Video Backend num_frames",
              "tags": [
                "third-party-advisory"
              ],
              "url": "https://www.vulncheck.com/advisories/vllm-0.30.0-before-0.31.0-resource-exhaustion-via-openpangu-video-backend-num-frames"
            }
          ],
          "title": "vLLM 0.30.0 before 0.31.0 Resource Exhaustion via OpenPangu Video Backend num_frames",
          "x_generator": {
            "engine": "vulncheck-endgame"
          }
        }
      },
      "cveMetadata": {
        "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "assignerShortName": "VulnCheck",
        "cveId": "CVE-2026-126394",
        "datePublished": "2026-11-13T09:35:52.305Z",
        "dateReserved": "2026-11-10T21:30:16.910Z",
        "dateUpdated": "2026-11-13T09:35:52.305Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-115918 (GCVE-0-2026-115918)

    Vulnerability from nvd – Published: 2026-10-26 17:21 – Updated: 2026-10-30 14:22
    VLAI
    Title
    vLLM: Responses API bypasses trust_request_chat_template for chat_template_kwargs
    Summary
    vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chat_template_kwargs[chat_template] when no server template is configured. ChatParams.get_apply_chat_template_kwargs() preserves that value without enforcing trust_request_chat_template, so the request can bypass the intended trust policy and cause CPU or memory exhaustion through Jinja rendering. This issue is fixed in version 0.32.0.
    SSVC
    Exploitation: none Automatable: no Technical Impact: partial
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-10-30 14:22 UTC
    CWE
    • CWE-400 - Uncontrolled Resource Consumption
    • CWE-770 - Allocation of Resources Without Limits or Throttling
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: >= 0.16.0, < 0.32.0
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-115918",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-10-30T14:22:12.561297Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-10-30T14:22:20.698Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 0.16.0, \u003c 0.32.0"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chat_template_kwargs[chat_template] when no server template is configured. ChatParams.get_apply_chat_template_kwargs() preserves that value without enforcing trust_request_chat_template, so the request can bypass the intended trust policy and cause CPU or memory exhaustion through Jinja rendering. This issue is fixed in version 0.32.0."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 6.5,
                "baseSeverity": "MEDIUM",
                "confidentialityImpact": "NONE",
                "integrityImpact": "NONE",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-400",
                  "description": "CWE-400: Uncontrolled Resource Consumption",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-770",
                  "description": "CWE-770: Allocation of Resources Without Limits or Throttling",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-10-26T17:21:49.719Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-x567-49g5-p4cf",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-x567-49g5-p4cf"
            },
            {
              "name": "https://github.com/vllm-project/vllm/pull/50300",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/pull/50300"
            },
            {
              "name": "https://github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134"
            },
            {
              "name": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"
            }
          ],
          "source": {
            "advisory": "GHSA-x567-49g5-p4cf",
            "discovery": "UNKNOWN"
          },
          "title": "vLLM: Responses API bypasses trust_request_chat_template for chat_template_kwargs"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-115918",
        "datePublished": "2026-10-26T17:21:49.719Z",
        "dateReserved": "2026-10-23T20:21:45.107Z",
        "dateUpdated": "2026-10-30T14:22:20.698Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-115917 (GCVE-0-2026-115917)

    Vulnerability from nvd – Published: 2026-10-26 17:20 – Updated: 2026-10-31 01:38
    VLAI
    Title
    vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server
    Summary
    vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the OpenAI-compatible server configures Starlette CORSMiddleware with allowed_origins set to a wildcard by default. A malicious web page can use a victim's browser to reach an unauthenticated vLLM server on localhost, an internal network, or a VPN, call endpoints including GET /v1/models and POST /v1/chat/completions, consume GPU resources, and read responses. Cookie-based cross-site request forgery does not apply because credentials are disabled by default, and deployments requiring bearer authentication are exposed only when the caller already has a usable token. This issue is fixed in version 0.32.0.
    SSVC
    Exploitation: none Automatable: no Technical Impact: partial
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-10-31 01:38 UTC
    CWE
    • CWE-942 - Permissive Cross-domain Policy with Untrusted Domains
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: < 0.32.0
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-115917",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-10-31T01:38:43.564283Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-10-31T01:38:53.155Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 0.32.0"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the OpenAI-compatible server configures Starlette CORSMiddleware with allowed_origins set to a wildcard by default. A malicious web page can use a victim\u0027s browser to reach an unauthenticated vLLM server on localhost, an internal network, or a VPN, call endpoints including GET /v1/models and POST /v1/chat/completions, consume GPU resources, and read responses. Cookie-based cross-site request forgery does not apply because credentials are disabled by default, and deployments requiring bearer authentication are exposed only when the caller already has a usable token. This issue is fixed in version 0.32.0."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "HIGH",
                "attackVector": "NETWORK",
                "availabilityImpact": "NONE",
                "baseScore": 3.4,
                "baseSeverity": "LOW",
                "confidentialityImpact": "LOW",
                "integrityImpact": "NONE",
                "privilegesRequired": "NONE",
                "scope": "CHANGED",
                "userInteraction": "REQUIRED",
                "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:L/I:N/A:N",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-942",
                  "description": "CWE-942: Permissive Cross-domain Policy with Untrusted Domains",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-10-26T17:20:09.065Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-vvpg-rrww-wpmh",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-vvpg-rrww-wpmh"
            },
            {
              "name": "https://github.com/vllm-project/vllm/pull/61009",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/pull/61009"
            },
            {
              "name": "https://github.com/vllm-project/vllm/commit/fcae5c98870ff2c20659731dce7ba3a3ff0d48aa",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/commit/fcae5c98870ff2c20659731dce7ba3a3ff0d48aa"
            },
            {
              "name": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"
            }
          ],
          "source": {
            "advisory": "GHSA-vvpg-rrww-wpmh",
            "discovery": "UNKNOWN"
          },
          "title": "vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-115917",
        "datePublished": "2026-10-26T17:20:09.065Z",
        "dateReserved": "2026-10-23T20:21:45.107Z",
        "dateUpdated": "2026-10-31T01:38:53.155Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-115916 (GCVE-0-2026-115916)

    Vulnerability from nvd – Published: 2026-10-26 17:18 – Updated: 2026-11-02 17:50
    VLAI
    Title
    vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)
    Summary
    vLLM is an inference and serving engine for large language models. Prior to 0.32.0, vllm/tokenizers/hf.py computes max_token_id with an off-by-one upper bound, allowing a pre-tokenized prompt ID equal to the vocabulary size to pass validation. For a tensor-parallel size of one and an exact multiple-of-64 vocabulary, VocabParallelEmbedding.forward does not mask that value before F.embedding uses it, causing a CUDA device-side assertion and terminating the engine. This issue is fixed in version 0.32.0.
    SSVC
    Exploitation: none Automatable: no Technical Impact: partial
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-11-02 17:49 UTC
    CWE
    • CWE-129 - Improper Validation of Array Index
    • CWE-193 - Off-by-one Error
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: < 0.32.0
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-115916",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-11-02T17:49:45.650631Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-11-02T17:50:28.478Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 0.32.0"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM is an inference and serving engine for large language models. Prior to 0.32.0, vllm/tokenizers/hf.py computes max_token_id with an off-by-one upper bound, allowing a pre-tokenized prompt ID equal to the vocabulary size to pass validation. For a tensor-parallel size of one and an exact multiple-of-64 vocabulary, VocabParallelEmbedding.forward does not mask that value before F.embedding uses it, causing a CUDA device-side assertion and terminating the engine. This issue is fixed in version 0.32.0."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 6.5,
                "baseSeverity": "MEDIUM",
                "confidentialityImpact": "NONE",
                "integrityImpact": "NONE",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-129",
                  "description": "CWE-129: Improper Validation of Array Index",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-193",
                  "description": "CWE-193: Off-by-one Error",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-10-26T17:18:17.582Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-q97c-p368-75c4",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-q97c-p368-75c4"
            },
            {
              "name": "https://github.com/vllm-project/vllm/pull/59491",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/pull/59491"
            },
            {
              "name": "https://github.com/vllm-project/vllm/commit/37cecc8141e2dcba9dd534897a164d4baaf27229",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/commit/37cecc8141e2dcba9dd534897a164d4baaf27229"
            },
            {
              "name": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"
            }
          ],
          "source": {
            "advisory": "GHSA-q97c-p368-75c4",
            "discovery": "UNKNOWN"
          },
          "title": "vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-115916",
        "datePublished": "2026-10-26T17:18:17.582Z",
        "dateReserved": "2026-10-23T20:21:45.107Z",
        "dateUpdated": "2026-11-02T17:50:28.478Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-115915 (GCVE-0-2026-115915)

    Vulnerability from nvd – Published: 2026-10-26 17:16 – Updated: 2026-10-26 19:35
    VLAI
    Title
    vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE
    Summary
    vLLM is an inference and serving engine for large language models. Prior to 0.32.0, ImageMediaIO passes attacker-controlled image bytes to Pillow through Image.open(BytesIO(data)) without restricting decoder selection, and the MIME label does not constrain the selected format. Image-capable request paths through parse_image() and fetch_image() can therefore dispatch an EPS payload to host components. A host with Ghostscript affected by CVE-2024-29510 can execute commands with the vLLM process's privileges, while environments using Pillow 12.0.0 through 12.2.0 can trigger CVE-2026-59203 and exhaust media-loading workers. Deployments without the applicable vulnerable dependency are not affected by that corresponding impact. This issue is fixed in version 0.32.0.
    SSVC
    Exploitation: none Automatable: no Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-10-26 19:31 UTC
    CWE
    • CWE-20 - Improper Input Validation
    • CWE-183 - Permissive List of Allowed Inputs
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: < 0.32.0
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-115915",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-10-26T19:31:21.498549Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-10-26T19:35:10.423Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 0.32.0"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM is an inference and serving engine for large language models. Prior to 0.32.0, ImageMediaIO passes attacker-controlled image bytes to Pillow through Image.open(BytesIO(data)) without restricting decoder selection, and the MIME label does not constrain the selected format. Image-capable request paths through parse_image() and fetch_image() can therefore dispatch an EPS payload to host components. A host with Ghostscript affected by CVE-2024-29510 can execute commands with the vLLM process\u0027s privileges, while environments using Pillow 12.0.0 through 12.2.0 can trigger CVE-2026-59203 and exhaust media-loading workers. Deployments without the applicable vulnerable dependency are not affected by that corresponding impact. This issue is fixed in version 0.32.0."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "HIGH",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 8.1,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-20",
                  "description": "CWE-20: Improper Input Validation",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-183",
                  "description": "CWE-183: Permissive List of Allowed Inputs",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-10-26T17:16:57.526Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-h3rc-j82p-2c3h",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-h3rc-j82p-2c3h"
            },
            {
              "name": "https://github.com/vllm-project/vllm/pull/60022",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/pull/60022"
            },
            {
              "name": "https://github.com/vllm-project/vllm/commit/710ac56e691d4713feca50a43e6c440f07d373fd",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/commit/710ac56e691d4713feca50a43e6c440f07d373fd"
            },
            {
              "name": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"
            }
          ],
          "source": {
            "advisory": "GHSA-h3rc-j82p-2c3h",
            "discovery": "UNKNOWN"
          },
          "title": "vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-115915",
        "datePublished": "2026-10-26T17:16:06.387Z",
        "dateReserved": "2026-10-23T20:21:45.107Z",
        "dateUpdated": "2026-10-26T19:35:10.423Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-115914 (GCVE-0-2026-115914)

    Vulnerability from nvd – Published: 2026-10-26 17:08 – Updated: 2026-10-30 14:23
    VLAI
    Title
    vLLM DeepSeek-OCR image processing vulnerable to denial of service
    Summary
    vLLM is an inference and serving engine for large language models. From 0.11.1 until 0.32.0, the DeepSeek-OCR, DeepSeek-OCR-2, and Unlimited-OCR image path allows a remote client that can reach the OpenAI-compatible API to submit a legal image whose normalized pixels sum to zero when that image is alone in its per-step encoder batch. _parse_and_validate_image_input returns no embedding, embed_multimodal propagates that value, and sanity_check_mm_encoder_outputs triggers a fatal assertion that shuts down the engine for all users. This issue is fixed in version 0.32.0.
    SSVC
    Exploitation: none Automatable: no Technical Impact: partial
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-10-30 14:23 UTC
    CWE
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: >= 0.11.1, < 0.32.0
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-115914",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-10-30T14:23:13.354875Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-10-30T14:23:21.521Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 0.11.1, \u003c 0.32.0"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM is an inference and serving engine for large language models. From 0.11.1 until 0.32.0, the DeepSeek-OCR, DeepSeek-OCR-2, and Unlimited-OCR image path allows a remote client that can reach the OpenAI-compatible API to submit a legal image whose normalized pixels sum to zero when that image is alone in its per-step encoder batch. _parse_and_validate_image_input returns no embedding, embed_multimodal propagates that value, and sanity_check_mm_encoder_outputs triggers a fatal assertion that shuts down the engine for all users. This issue is fixed in version 0.32.0."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 6.5,
                "baseSeverity": "MEDIUM",
                "confidentialityImpact": "NONE",
                "integrityImpact": "NONE",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-617",
                  "description": "CWE-617: Reachable Assertion",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-10-26T17:08:20.839Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-gq5q-89c7-vhvx",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-gq5q-89c7-vhvx"
            },
            {
              "name": "https://github.com/vllm-project/vllm/pull/59417",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/pull/59417"
            },
            {
              "name": "https://github.com/vllm-project/vllm/commit/c15672cfb49152ebf65cfd188e71b84593ec5686",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/commit/c15672cfb49152ebf65cfd188e71b84593ec5686"
            },
            {
              "name": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"
            }
          ],
          "source": {
            "advisory": "GHSA-gq5q-89c7-vhvx",
            "discovery": "UNKNOWN"
          },
          "title": "vLLM DeepSeek-OCR image processing vulnerable to denial of service"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-115914",
        "datePublished": "2026-10-26T17:08:20.839Z",
        "dateReserved": "2026-10-23T20:21:45.107Z",
        "dateUpdated": "2026-10-30T14:23:21.521Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-115913 (GCVE-0-2026-115913)

    Vulnerability from nvd – Published: 2026-10-26 16:56 – Updated: 2026-11-02 17:48
    VLAI
    Title
    vLLM: Phi-4 multimodal audio encoder materializes and retains full attention matrices: a single max-length audio OOM-crashes the vLLM engine
    Summary
    vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the Phi-4 multimodal audio encoder in phi4mm_audio.py and phi4mm_utils.py uses eager attention by default, allowing a remote client to submit one legal long audio clip that causes MultiHeadedAttention.forward_attention to materialize and retain full attention matrices in self.attn. The scaled dot-product attention branch does not materialize these matrices. The resulting quadratic GPU-memory use can cause an out-of-memory condition and terminate EngineCore for all users. This issue is fixed in version 0.32.0.
    SSVC
    Exploitation: none Automatable: no Technical Impact: partial
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-11-02 17:48 UTC
    CWE
    • CWE-770 - Allocation of Resources Without Limits or Throttling
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: < 0.32.0
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-115913",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-11-02T17:48:03.108418Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-11-02T17:48:14.216Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 0.32.0"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the Phi-4 multimodal audio encoder in phi4mm_audio.py and phi4mm_utils.py uses eager attention by default, allowing a remote client to submit one legal long audio clip that causes MultiHeadedAttention.forward_attention to materialize and retain full attention matrices in self.attn. The scaled dot-product attention branch does not materialize these matrices. The resulting quadratic GPU-memory use can cause an out-of-memory condition and terminate EngineCore for all users. This issue is fixed in version 0.32.0."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 6.5,
                "baseSeverity": "MEDIUM",
                "confidentialityImpact": "NONE",
                "integrityImpact": "NONE",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-770",
                  "description": "CWE-770: Allocation of Resources Without Limits or Throttling",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-10-26T16:56:59.817Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8397-8qf6-f2gm",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8397-8qf6-f2gm"
            },
            {
              "name": "https://github.com/vllm-project/vllm/pull/60614",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/pull/60614"
            },
            {
              "name": "https://github.com/vllm-project/vllm/commit/3d52578e13454de0bb8352cac988347cdcc89928",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/commit/3d52578e13454de0bb8352cac988347cdcc89928"
            },
            {
              "name": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"
            }
          ],
          "source": {
            "advisory": "GHSA-8397-8qf6-f2gm",
            "discovery": "UNKNOWN"
          },
          "title": "vLLM: Phi-4 multimodal audio encoder materializes and retains full attention matrices: a single max-length audio OOM-crashes the vLLM engine"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-115913",
        "datePublished": "2026-10-26T16:56:59.817Z",
        "dateReserved": "2026-10-23T20:21:45.107Z",
        "dateUpdated": "2026-11-02T17:48:14.216Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-115912 (GCVE-0-2026-115912)

    Vulnerability from nvd – Published: 2026-10-26 16:54 – Updated: 2026-10-26 19:35
    VLAI
    Title
    vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled
    Summary
    vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonic_id values in public multimodal features.kwargs_data. In scale-out deployments with shared-memory multimodal caching enabled, workers trust those values and pass attacker-selected bytes to pickle.loads(), allowing arbitrary Python execution even when insecure serialization is disabled. This issue is fixed in version 0.32.0.
    SSVC
    Exploitation: none Automatable: no Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-10-26 19:31 UTC
    CWE
    • CWE-502 - Deserialization of Untrusted Data
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: < 0.32.0
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-115912",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-10-26T19:31:18.550495Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-10-26T19:35:42.879Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 0.32.0"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonic_id values in public multimodal features.kwargs_data. In scale-out deployments with shared-memory multimodal caching enabled, workers trust those values and pass attacker-selected bytes to pickle.loads(), allowing arbitrary Python execution even when insecure serialization is disabled. This issue is fixed in version 0.32.0."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "HIGH",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 7.5,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-502",
                  "description": "CWE-502: Deserialization of Untrusted Data",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-10-26T16:54:00.643Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-6757-hggm-hp2w",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-6757-hggm-hp2w"
            },
            {
              "name": "https://github.com/vllm-project/vllm/pull/59357",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/pull/59357"
            },
            {
              "name": "https://github.com/vllm-project/vllm/commit/3d5625cc3c2474994107047d7a6ecb8e4008f9b0",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/commit/3d5625cc3c2474994107047d7a6ecb8e4008f9b0"
            },
            {
              "name": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"
            }
          ],
          "source": {
            "advisory": "GHSA-6757-hggm-hp2w",
            "discovery": "UNKNOWN"
          },
          "title": "vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-115912",
        "datePublished": "2026-10-26T16:54:00.643Z",
        "dateReserved": "2026-10-23T20:21:45.107Z",
        "dateUpdated": "2026-10-26T19:35:42.879Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-115911 (GCVE-0-2026-115911)

    Vulnerability from nvd – Published: 2026-10-26 16:47 – Updated: 2026-10-30 14:20
    VLAI
    Title
    vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool
    Summary
    vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.32.0, authenticated callers can supply a request chat template when no server-side --chat-template is configured, or a malicious model repository can provide a template that is compiled and rendered by tokenizer.apply_chat_template() without a wall-clock timeout, output-size limit, or iteration bound. Rendering runs in a ThreadPoolExecutor with one worker by default, so a nonterminating render can block /v1/responses and other chat-template users after the request ends, while an output-expanding render can exhaust server memory. Harmony models are not affected because they do not use this Jinja path. This issue is fixed in version 0.32.0.
    SSVC
    Exploitation: none Automatable: no Technical Impact: partial
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-10-30 14:20 UTC
    CWE
    • CWE-400 - Uncontrolled Resource Consumption
    • CWE-770 - Allocation of Resources Without Limits or Throttling
    • CWE-834 - Excessive Iteration
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: >= 0.19.0, < 0.32.0
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-115911",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-10-30T14:20:35.704686Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-10-30T14:20:51.484Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 0.19.0, \u003c 0.32.0"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.32.0, authenticated callers can supply a request chat template when no server-side --chat-template is configured, or a malicious model repository can provide a template that is compiled and rendered by tokenizer.apply_chat_template() without a wall-clock timeout, output-size limit, or iteration bound. Rendering runs in a ThreadPoolExecutor with one worker by default, so a nonterminating render can block /v1/responses and other chat-template users after the request ends, while an output-expanding render can exhaust server memory. Harmony models are not affected because they do not use this Jinja path. This issue is fixed in version 0.32.0."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 6.5,
                "baseSeverity": "MEDIUM",
                "confidentialityImpact": "NONE",
                "integrityImpact": "NONE",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-400",
                  "description": "CWE-400: Uncontrolled Resource Consumption",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-770",
                  "description": "CWE-770: Allocation of Resources Without Limits or Throttling",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-834",
                  "description": "CWE-834: Excessive Iteration",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-10-26T16:47:59.377Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-542m-9234-8gvf",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-542m-9234-8gvf"
            },
            {
              "name": "https://github.com/vllm-project/vllm/pull/50300",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/pull/50300"
            },
            {
              "name": "https://github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134"
            },
            {
              "name": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"
            }
          ],
          "source": {
            "advisory": "GHSA-542m-9234-8gvf",
            "discovery": "UNKNOWN"
          },
          "title": "vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-115911",
        "datePublished": "2026-10-26T16:47:59.377Z",
        "dateReserved": "2026-10-23T20:21:45.107Z",
        "dateUpdated": "2026-10-30T14:20:51.484Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-129356 (GCVE-0-2026-129356)

    Vulnerability from cvelistv5 – Published: 2026-11-15 01:15 – Updated: 2026-11-16 15:37 X_Open Source
    VLAI
    Title
    vllm-project vllm Common Prefix single_type_kv_cache_manager.py race condition
    Summary
    A vulnerability was found in vllm-project vllm 0.30.0/0.31.0. This vulnerability affects unknown code of the file single_type_kv_cache_manager.py of the component Common Prefix Handler. The manipulation results in race condition. The attack may be performed from remote. Attacks of this nature are highly complex. It is stated that the exploitability is difficult. The exploit has been made public and could be used. Upgrading to version 0.32.0 is able to resolve this issue. The patch is identified as e687a251bb056fa527846633f7a1b0a6c0f42374. You should upgrade the affected component.
    SSVC
    Exploitation: poc Automatable: no Technical Impact: partial
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-11-16 15:12 UTC
    CWE
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: 0.30.0
    Affected: 0.31.0
    Unaffected: 0.32.0
        cpe:2.3:a:vllm-project:vllm:*:*:*:*:*:*:*:*
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-129356",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-11-16T15:12:04.729936Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-11-16T15:37:21.853Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "cpes": [
                "cpe:2.3:a:vllm-project:vllm:*:*:*:*:*:*:*:*"
              ],
              "modules": [
                "Common Prefix Handler"
              ],
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "status": "affected",
                  "version": "0.30.0"
                },
                {
                  "status": "affected",
                  "version": "0.31.0"
                },
                {
                  "status": "unaffected",
                  "version": "0.32.0"
                }
              ]
            }
          ],
          "credits": [
            {
              "lang": "en",
              "type": "reporter",
              "value": "Zyz3366 (VulDB User)"
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "A vulnerability was found in vllm-project vllm 0.30.0/0.31.0. This vulnerability affects unknown code of the file single_type_kv_cache_manager.py of the component Common Prefix Handler. The manipulation results in race condition. The attack may be performed from remote. Attacks of this nature are highly complex. It is stated that the exploitability is difficult. The exploit has been made public and could be used. Upgrading to version 0.32.0 is able to resolve this issue. The patch is identified as e687a251bb056fa527846633f7a1b0a6c0f42374. You should upgrade the affected component."
            }
          ],
          "metrics": [
            {
              "cvssV4_0": {
                "baseScore": 2.3,
                "baseSeverity": "LOW",
                "vectorString": "CVSS:4.0/AV:N/AC:H/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P",
                "version": "4.0"
              }
            },
            {
              "cvssV3_1": {
                "baseScore": 5,
                "baseSeverity": "MEDIUM",
                "vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:L/I:L/A:L/E:P/RL:O/RC:C",
                "version": "3.1"
              }
            },
            {
              "cvssV3_0": {
                "baseScore": 5,
                "baseSeverity": "MEDIUM",
                "vectorString": "CVSS:3.0/AV:N/AC:H/PR:L/UI:N/S:U/C:L/I:L/A:L/E:P/RL:O/RC:C",
                "version": "3.0"
              }
            },
            {
              "cvssV2_0": {
                "baseScore": 4.6,
                "vectorString": "AV:N/AC:H/Au:S/C:P/I:P/A:P/E:POC/RL:OF/RC:C",
                "version": "2.0"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-362",
                  "description": "Race Condition",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-11-15T01:15:24.018Z",
            "orgId": "1af790b2-7ee1-4545-860a-a788eba489b5",
            "shortName": "VulDB"
          },
          "references": [
            {
              "name": "VDB-437419 | vllm-project vllm Common Prefix single_type_kv_cache_manager.py race condition",
              "tags": [
                "vdb-entry"
              ],
              "url": "https://vuldb.com/vuln/437419"
            },
            {
              "name": "VDB-437419 | CTI Indicators (IOB, IOC, IOA)",
              "tags": [
                "signature",
                "permissions-required"
              ],
              "url": "https://vuldb.com/vuln/437419/cti"
            },
            {
              "name": "CVE-2026-129356 | CVE Analysis and Report",
              "tags": [
                "third-party-advisory"
              ],
              "url": "https://vuldb.com/cve/CVE-2026-129356"
            },
            {
              "name": "Submit #1043823 | vLLM Project vLLM v0.30.0, v0.31.0 Improper Resource Management",
              "tags": [
                "third-party-advisory"
              ],
              "url": "https://vuldb.com/submit/1043823"
            },
            {
              "tags": [
                "exploit",
                "issue-tracking"
              ],
              "url": "https://github.com/vllm-project/vllm/issues/61673"
            },
            {
              "tags": [
                "issue-tracking",
                "patch"
              ],
              "url": "https://github.com/vllm-project/vllm/pull/61126"
            },
            {
              "tags": [
                "patch"
              ],
              "url": "https://github.com/vllm-project/vllm/commit/e687a251bb056fa527846633f7a1b0a6c0f42374"
            },
            {
              "tags": [
                "patch"
              ],
              "url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"
            },
            {
              "tags": [
                "product"
              ],
              "url": "https://github.com/vllm-project/vllm/"
            }
          ],
          "tags": [
            "x_open-source"
          ],
          "timeline": [
            {
              "lang": "en",
              "time": "2026-11-14T00:00:00.000Z",
              "value": "Advisory disclosed"
            },
            {
              "lang": "en",
              "time": "2026-11-14T01:00:00.000Z",
              "value": "VulDB entry created"
            },
            {
              "lang": "en",
              "time": "2026-11-14T07:47:52.000Z",
              "value": "VulDB entry last update"
            }
          ],
          "title": "vllm-project vllm Common Prefix single_type_kv_cache_manager.py race condition",
          "x_generator": [
            "VulDB PVTS v202611"
          ]
        }
      },
      "cveMetadata": {
        "assignerOrgId": "1af790b2-7ee1-4545-860a-a788eba489b5",
        "assignerShortName": "VulDB",
        "cveId": "CVE-2026-129356",
        "datePublished": "2026-11-15T01:15:24.018Z",
        "dateReserved": "2026-11-14T06:42:47.336Z",
        "dateUpdated": "2026-11-16T15:37:21.853Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-126394 (GCVE-0-2026-126394)

    Vulnerability from cvelistv5 – Published: 2026-11-13 09:35 – Updated: 2026-11-13 09:35
    VLAI
    Title
    vLLM 0.30.0 before 0.31.0 Resource Exhaustion via OpenPangu Video Backend num_frames
    Summary
    vLLM 0.30.0 before 0.31.0 contains a resource exhaustion vulnerability in OpenCVDynamicOpenPanguVideoBackend, which uses request-controlled num_frames without an effective ceiling. Unauthenticated attackers can send /v1/chat/completions or /tokenize requests selecting the openpangu video_backend with a huge num_frames, forcing np.linspace allocations and CPU work that OOM-kill the API server.
    CWE
    • CWE-770 - Allocation of Resources Without Limits or Throttling
    References
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: 0.30.0 , < 0.31.0 (semver)
    Unaffected: 0.31.0 (semver)
        cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
    Create a notification for this product.
    Date Public
    2026-10-27 00:00
    Show details on NVD website

    {
      "containers": {
        "cna": {
          "affected": [
            {
              "defaultStatus": "unaffected",
              "packageURL": "pkg:pypi/vllm",
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "lessThan": "0.31.0",
                  "status": "affected",
                  "version": "0.30.0",
                  "versionType": "semver"
                },
                {
                  "status": "unaffected",
                  "version": "0.31.0",
                  "versionType": "semver"
                }
              ]
            }
          ],
          "cpeApplicability": [
            {
              "nodes": [
                {
                  "cpeMatch": [
                    {
                      "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
                      "versionEndExcluding": "0.31.0",
                      "versionStartIncluding": "0.30.0",
                      "vulnerable": true
                    }
                  ],
                  "negate": false,
                  "operator": "OR"
                }
              ]
            }
          ],
          "credits": [
            {
              "lang": "en",
              "type": "reporter",
              "value": "gn00295120"
            },
            {
              "lang": "en",
              "type": "coordinator",
              "value": "jperezdealgaba"
            }
          ],
          "datePublic": "2026-10-27T00:00:00.000Z",
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM 0.30.0 before 0.31.0 contains a resource exhaustion vulnerability in OpenCVDynamicOpenPanguVideoBackend, which uses request-controlled num_frames without an effective ceiling. Unauthenticated attackers can send /v1/chat/completions or /tokenize requests selecting the openpangu video_backend with a huge num_frames, forcing np.linspace allocations and CPU work that OOM-kill the API server."
            }
          ],
          "metrics": [
            {
              "cvssV4_0": {
                "attackComplexity": "LOW",
                "attackRequirements": "NONE",
                "attackVector": "NETWORK",
                "baseScore": 6.9,
                "baseSeverity": "MEDIUM",
                "privilegesRequired": "NONE",
                "subAvailabilityImpact": "NONE",
                "subConfidentialityImpact": "NONE",
                "subIntegrityImpact": "NONE",
                "userInteraction": "NONE",
                "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N",
                "version": "4.0",
                "vulnAvailabilityImpact": "LOW",
                "vulnConfidentialityImpact": "NONE",
                "vulnIntegrityImpact": "NONE"
              },
              "format": "CVSS"
            },
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "LOW",
                "baseScore": 5.3,
                "baseSeverity": "MEDIUM",
                "confidentialityImpact": "NONE",
                "integrityImpact": "NONE",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L",
                "version": "3.1"
              },
              "format": "CVSS"
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-770",
                  "description": "Allocation of Resources Without Limits or Throttling",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-11-13T09:35:52.305Z",
            "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
            "shortName": "VulnCheck"
          },
          "references": [
            {
              "name": "GitHub Security Advisory (GHSA-894j-wg8m-63h8)",
              "tags": [
                "vendor-advisory"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-894j-wg8m-63h8"
            },
            {
              "name": "VulnCheck Advisory: vLLM 0.30.0 before 0.31.0 Resource Exhaustion via OpenPangu Video Backend num_frames",
              "tags": [
                "third-party-advisory"
              ],
              "url": "https://www.vulncheck.com/advisories/vllm-0.30.0-before-0.31.0-resource-exhaustion-via-openpangu-video-backend-num-frames"
            }
          ],
          "title": "vLLM 0.30.0 before 0.31.0 Resource Exhaustion via OpenPangu Video Backend num_frames",
          "x_generator": {
            "engine": "vulncheck-endgame"
          }
        }
      },
      "cveMetadata": {
        "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "assignerShortName": "VulnCheck",
        "cveId": "CVE-2026-126394",
        "datePublished": "2026-11-13T09:35:52.305Z",
        "dateReserved": "2026-11-10T21:30:16.910Z",
        "dateUpdated": "2026-11-13T09:35:52.305Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-126395 (GCVE-0-2026-126395)

    Vulnerability from cvelistv5 – Published: 2026-11-13 09:35 – Updated: 2026-11-13 22:30
    VLAI
    Title
    vLLM 0.14.0rc1 before 0.31.0 Heap Address Disclosure via sanitize_message()
    Summary
    vLLM from 0.14.0rc1 before 0.31.0 contains an information disclosure vulnerability in sanitize_message() whose lowercase-only regex fails to scrub uppercase PIL image addresses. Unauthenticated attackers can send a crafted PNG to endpoints such as /tokenize, triggering HF-processor errors that leak live server heap addresses useful for ASLR bypass.
    SSVC
    Exploitation: none Automatable: yes Technical Impact: partial
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-11-13 16:34 UTC
    CWE
    • CWE-532 - Insertion of Sensitive Information into Log File
    References
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: 0.14.0rc1 , < 0.31.0 (custom)
    Unaffected: 0.31.0 (custom)
        cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
    Create a notification for this product.
    Date Public
    2026-10-27 00:00
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-126395",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-11-13T16:34:31.048655Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-11-13T22:30:11.255Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "defaultStatus": "unaffected",
              "packageURL": "pkg:pypi/vllm",
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "lessThan": "0.31.0",
                  "status": "affected",
                  "version": "0.14.0rc1",
                  "versionType": "custom"
                },
                {
                  "status": "unaffected",
                  "version": "0.31.0",
                  "versionType": "custom"
                }
              ]
            }
          ],
          "cpeApplicability": [
            {
              "nodes": [
                {
                  "cpeMatch": [
                    {
                      "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
                      "versionEndExcluding": "0.31.0",
                      "versionStartIncluding": "0.14.0rc1",
                      "vulnerable": true
                    }
                  ],
                  "negate": false,
                  "operator": "OR"
                }
              ]
            }
          ],
          "credits": [
            {
              "lang": "en",
              "type": "reporter",
              "value": "0xiviel"
            },
            {
              "lang": "en",
              "type": "coordinator",
              "value": "jperezdealgaba"
            },
            {
              "lang": "en",
              "type": "remediation developer",
              "value": "DarkLight1337"
            }
          ],
          "datePublic": "2026-10-27T00:00:00.000Z",
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM from 0.14.0rc1 before 0.31.0 contains an information disclosure vulnerability in sanitize_message() whose lowercase-only regex fails to scrub uppercase PIL image addresses. Unauthenticated attackers can send a crafted PNG to endpoints such as /tokenize, triggering HF-processor errors that leak live server heap addresses useful for ASLR bypass."
            }
          ],
          "metrics": [
            {
              "cvssV4_0": {
                "attackComplexity": "LOW",
                "attackRequirements": "NONE",
                "attackVector": "NETWORK",
                "baseScore": 6.9,
                "baseSeverity": "MEDIUM",
                "privilegesRequired": "NONE",
                "subAvailabilityImpact": "NONE",
                "subConfidentialityImpact": "NONE",
                "subIntegrityImpact": "NONE",
                "userInteraction": "NONE",
                "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:N/VA:N/SC:N/SI:N/SA:N",
                "version": "4.0",
                "vulnAvailabilityImpact": "NONE",
                "vulnConfidentialityImpact": "LOW",
                "vulnIntegrityImpact": "NONE"
              },
              "format": "CVSS"
            },
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "NONE",
                "baseScore": 5.3,
                "baseSeverity": "MEDIUM",
                "confidentialityImpact": "LOW",
                "integrityImpact": "NONE",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N",
                "version": "3.1"
              },
              "format": "CVSS"
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-532",
                  "description": "Insertion of Sensitive Information into Log File",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-11-13T09:35:51.636Z",
            "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
            "shortName": "VulnCheck"
          },
          "references": [
            {
              "name": "GitHub Security Advisory (GHSA-m9fg-w9qh-67pc)",
              "tags": [
                "vendor-advisory"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-m9fg-w9qh-67pc"
            },
            {
              "name": "VulnCheck Advisory: vLLM 0.14.0rc1 before 0.31.0 Heap Address Disclosure via sanitize_message()",
              "tags": [
                "third-party-advisory"
              ],
              "url": "https://www.vulncheck.com/advisories/vllm-0.14-0rc1-before-0.31.0-heap-address-disclosure-via-sanitize-message"
            }
          ],
          "title": "vLLM 0.14.0rc1 before 0.31.0 Heap Address Disclosure via sanitize_message()",
          "x_generator": {
            "engine": "vulncheck-endgame"
          }
        }
      },
      "cveMetadata": {
        "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "assignerShortName": "VulnCheck",
        "cveId": "CVE-2026-126395",
        "datePublished": "2026-11-13T09:35:51.636Z",
        "dateReserved": "2026-11-10T21:30:16.910Z",
        "dateUpdated": "2026-11-13T22:30:11.255Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-126396 (GCVE-0-2026-126396)

    Vulnerability from cvelistv5 – Published: 2026-11-13 09:35 – Updated: 2026-11-13 20:27
    VLAI
    Title
    vLLM from 0.24.0 before 0.31.0 Resource Exhaustion via MiniMax M3 min_pixels
    Summary
    vLLM from 0.24.0 before 0.31.0 contains a resource exhaustion vulnerability in the MiniMax M3 VL video processor, which accepts request-level min_pixels without range or min_pixels <= max_pixels validation. Its video-wide pixel budget is enforced only when max_long_side_pixel is set, and that value defaults to None. API clients can supply a large min_pixels via mm_processor_kwargs to enlarge every decoded frame, causing excessive CPU and host-memory consumption that may disrupt workers or the service.
    SSVC
    Exploitation: none Automatable: yes Technical Impact: partial
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-11-13 20:27 UTC
    CWE
    • CWE-770 - Allocation of Resources Without Limits or Throttling
    References
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: 0.24.0 , < 0.31.0 (semver)
    Unaffected: 0.31.0 (semver)
        cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
    Create a notification for this product.
    Date Public
    2026-10-27 00:00
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-126396",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-11-13T20:27:09.832988Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-11-13T20:27:21.640Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "defaultStatus": "unaffected",
              "packageURL": "pkg:pypi/vllm",
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "lessThan": "0.31.0",
                  "status": "affected",
                  "version": "0.24.0",
                  "versionType": "semver"
                },
                {
                  "status": "unaffected",
                  "version": "0.31.0",
                  "versionType": "semver"
                }
              ]
            }
          ],
          "cpeApplicability": [
            {
              "nodes": [
                {
                  "cpeMatch": [
                    {
                      "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
                      "versionEndExcluding": "0.31.0",
                      "versionStartIncluding": "0.24.0",
                      "vulnerable": true
                    }
                  ],
                  "operator": "OR"
                }
              ]
            }
          ],
          "credits": [
            {
              "lang": "en",
              "type": "reporter",
              "value": "mg-princess"
            },
            {
              "lang": "en",
              "type": "coordinator",
              "value": "jperezdealgaba"
            }
          ],
          "datePublic": "2026-10-27T00:00:00.000Z",
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM from 0.24.0 before 0.31.0 contains a resource exhaustion vulnerability in the MiniMax M3 VL video processor, which accepts request-level min_pixels without range or min_pixels \u003c= max_pixels validation. Its video-wide pixel budget is enforced only when max_long_side_pixel is set, and that value defaults to None. API clients can supply a large min_pixels via mm_processor_kwargs to enlarge every decoded frame, causing excessive CPU and host-memory consumption that may disrupt workers or the service."
            }
          ],
          "metrics": [
            {
              "cvssV4_0": {
                "Automatable": "NOT_DEFINED",
                "Recovery": "NOT_DEFINED",
                "Safety": "NOT_DEFINED",
                "attackComplexity": "LOW",
                "attackRequirements": "NONE",
                "attackVector": "NETWORK",
                "baseScore": 6.9,
                "baseSeverity": "MEDIUM",
                "exploitMaturity": "NOT_DEFINED",
                "privilegesRequired": "NONE",
                "providerUrgency": "NOT_DEFINED",
                "subAvailabilityImpact": "NONE",
                "subConfidentialityImpact": "NONE",
                "subIntegrityImpact": "NONE",
                "userInteraction": "NONE",
                "valueDensity": "NOT_DEFINED",
                "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N",
                "version": "4.0",
                "vulnAvailabilityImpact": "LOW",
                "vulnConfidentialityImpact": "NONE",
                "vulnIntegrityImpact": "NONE",
                "vulnerabilityResponseEffort": "NOT_DEFINED"
              },
              "format": "CVSS",
              "scenarios": [
                {
                  "lang": "en",
                  "value": "GENERAL"
                }
              ]
            },
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "LOW",
                "baseScore": 5.3,
                "baseSeverity": "MEDIUM",
                "confidentialityImpact": "NONE",
                "integrityImpact": "NONE",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L",
                "version": "3.1"
              },
              "format": "CVSS",
              "scenarios": [
                {
                  "lang": "en",
                  "value": "GENERAL"
                }
              ]
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-770",
                  "description": "Allocation of Resources Without Limits or Throttling",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-11-13T11:44:37.122Z",
            "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
            "shortName": "VulnCheck"
          },
          "references": [
            {
              "name": "GitHub Security Advisory (GHSA-w4cg-mhc7-mgw3)",
              "tags": [
                "vendor-advisory"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-w4cg-mhc7-mgw3"
            },
            {
              "name": "VulnCheck Advisory: vLLM from 0.24.0 before 0.31.0 Resource Exhaustion via MiniMax M3 min_pixels",
              "tags": [
                "third-party-advisory"
              ],
              "url": "https://www.vulncheck.com/advisories/vllm-from-0.24.0-before-0.31.0-resource-exhaustion-via-minimax-m3-min-pixels"
            }
          ],
          "title": "vLLM from 0.24.0 before 0.31.0 Resource Exhaustion via MiniMax M3 min_pixels",
          "x_generator": {
            "engine": "vulncheck-endgame"
          }
        }
      },
      "cveMetadata": {
        "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "assignerShortName": "VulnCheck",
        "cveId": "CVE-2026-126396",
        "datePublished": "2026-11-13T09:35:50.950Z",
        "dateReserved": "2026-11-10T21:30:16.910Z",
        "dateUpdated": "2026-11-13T20:27:21.640Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-126397 (GCVE-0-2026-126397)

    Vulnerability from cvelistv5 – Published: 2026-11-13 09:35 – Updated: 2026-11-13 09:35
    VLAI
    Title
    vLLM 0.10.1 before 0.31.0 Cohere2 Vision DoS via max_patches
    Summary
    vLLM from 0.10.1 before 0.31.0 forwards a request-controlled mm_processor_kwargs.max_patches value to the Hugging Face processor for Cohere2 Vision models without a server-side upper bound, causing quadratic CPU work during multimodal preprocessing. Remote clients can send small image chat-completion requests with large, varying max_patches values to bypass the LRU cache, exhaust preprocessing workers, and deny service to other clients.
    CWE
    • CWE-400 - Uncontrolled Resource Consumption
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: 0.10.1 , < 0.31.0 (semver)
    Unaffected: 0.31.0 (semver)
        cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
    Create a notification for this product.
    Date Public
    2026-10-27 00:00
    Show details on NVD website

    {
      "containers": {
        "cna": {
          "affected": [
            {
              "defaultStatus": "unaffected",
              "packageURL": "pkg:pypi/vllm",
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "lessThan": "0.31.0",
                  "status": "affected",
                  "version": "0.10.1",
                  "versionType": "semver"
                },
                {
                  "status": "unaffected",
                  "version": "0.31.0",
                  "versionType": "semver"
                }
              ]
            }
          ],
          "cpeApplicability": [
            {
              "nodes": [
                {
                  "cpeMatch": [
                    {
                      "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
                      "versionEndExcluding": "0.31.0",
                      "versionStartIncluding": "0.10.1",
                      "vulnerable": true
                    }
                  ],
                  "negate": false,
                  "operator": "OR"
                }
              ]
            }
          ],
          "credits": [
            {
              "lang": "en",
              "type": "reporter",
              "value": "0xbbdd"
            },
            {
              "lang": "en",
              "type": "coordinator",
              "value": "jperezdealgaba"
            }
          ],
          "datePublic": "2026-10-27T00:00:00.000Z",
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM from 0.10.1 before 0.31.0 forwards a request-controlled mm_processor_kwargs.max_patches value to the Hugging Face processor for Cohere2 Vision models without a server-side upper bound, causing quadratic CPU work during multimodal preprocessing. Remote clients can send small image chat-completion requests with large, varying max_patches values to bypass the LRU cache, exhaust preprocessing workers, and deny service to other clients."
            }
          ],
          "metrics": [
            {
              "cvssV4_0": {
                "Automatable": "NOT_DEFINED",
                "Recovery": "NOT_DEFINED",
                "Safety": "NOT_DEFINED",
                "attackComplexity": "LOW",
                "attackRequirements": "NONE",
                "attackVector": "NETWORK",
                "baseScore": 8.7,
                "baseSeverity": "HIGH",
                "exploitMaturity": "NOT_DEFINED",
                "privilegesRequired": "NONE",
                "providerUrgency": "NOT_DEFINED",
                "subAvailabilityImpact": "NONE",
                "subConfidentialityImpact": "NONE",
                "subIntegrityImpact": "NONE",
                "userInteraction": "NONE",
                "valueDensity": "NOT_DEFINED",
                "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N",
                "version": "4.0",
                "vulnAvailabilityImpact": "HIGH",
                "vulnConfidentialityImpact": "NONE",
                "vulnIntegrityImpact": "NONE",
                "vulnerabilityResponseEffort": "NOT_DEFINED"
              },
              "format": "CVSS"
            },
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 7.5,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "NONE",
                "integrityImpact": "NONE",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H",
                "version": "3.1"
              },
              "format": "CVSS"
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-400",
                  "description": "Uncontrolled Resource Consumption",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-11-13T09:35:50.274Z",
            "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
            "shortName": "VulnCheck"
          },
          "references": [
            {
              "name": "GitHub Security Advisory (GHSA-9g3c-x747-c6wr)",
              "tags": [
                "vendor-advisory"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-9g3c-x747-c6wr"
            },
            {
              "name": "Patch Commit",
              "tags": [
                "patch"
              ],
              "url": "https://github.com/vllm-project/vllm/commit/f6326f53bda46898a331c2d24500332c285d9a2b"
            },
            {
              "name": "VulnCheck Advisory: vLLM 0.10.1 before 0.31.0 Cohere2 Vision DoS via max_patches",
              "tags": [
                "third-party-advisory"
              ],
              "url": "https://www.vulncheck.com/advisories/vllm-0.10.1-before-0.31.0-cohere2-vision-dos-via-max-patches"
            }
          ],
          "title": "vLLM 0.10.1 before 0.31.0 Cohere2 Vision DoS via max_patches",
          "x_generator": {
            "engine": "vulncheck-endgame"
          }
        }
      },
      "cveMetadata": {
        "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "assignerShortName": "VulnCheck",
        "cveId": "CVE-2026-126397",
        "datePublished": "2026-11-13T09:35:50.274Z",
        "dateReserved": "2026-11-10T21:30:16.910Z",
        "dateUpdated": "2026-11-13T09:35:50.274Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-126398 (GCVE-0-2026-126398)

    Vulnerability from cvelistv5 – Published: 2026-11-13 09:35 – Updated: 2026-11-13 09:35
    VLAI
    Title
    vLLM 0.28.0 before 0.30.0 Denial of Service via Prompt Embeds on XD-RoPE Models
    Summary
    vLLM from 0.28.0 before 0.30.0 contains a reachable assertion vulnerability in GPUModelRunner._init_xdrope_positions that allows remote attackers to crash the engine by submitting embeddings-only requests. Attackers can send a /v1/completions request containing only prompt_embeds to XD-RoPE models with --enable-prompt-embeds, terminating the EngineCore and API server for all clients.
    CWE
    References
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: 0.28.0 , < 0.30.0 (semver)
    Unaffected: 0.30.0 (semver)
        cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
    Create a notification for this product.
    Date Public
    2026-10-27 00:00
    Show details on NVD website

    {
      "containers": {
        "cna": {
          "affected": [
            {
              "defaultStatus": "unaffected",
              "packageURL": "pkg:pypi/vllm",
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "lessThan": "0.30.0",
                  "status": "affected",
                  "version": "0.28.0",
                  "versionType": "semver"
                },
                {
                  "status": "unaffected",
                  "version": "0.30.0",
                  "versionType": "semver"
                }
              ]
            }
          ],
          "cpeApplicability": [
            {
              "nodes": [
                {
                  "cpeMatch": [
                    {
                      "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
                      "versionEndExcluding": "0.30.0",
                      "versionStartIncluding": "0.28.0",
                      "vulnerable": true
                    }
                  ],
                  "negate": false,
                  "operator": "OR"
                }
              ]
            }
          ],
          "credits": [
            {
              "lang": "en",
              "type": "reporter",
              "value": "wildoranges"
            },
            {
              "lang": "en",
              "type": "coordinator",
              "value": "jperezdealgaba"
            }
          ],
          "datePublic": "2026-10-27T00:00:00.000Z",
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM from 0.28.0 before 0.30.0 contains a reachable assertion vulnerability in GPUModelRunner._init_xdrope_positions that allows remote attackers to crash the engine by submitting embeddings-only requests. Attackers can send a /v1/completions request containing only prompt_embeds to XD-RoPE models with --enable-prompt-embeds, terminating the EngineCore and API server for all clients."
            }
          ],
          "metrics": [
            {
              "cvssV4_0": {
                "attackComplexity": "HIGH",
                "attackRequirements": "PRESENT",
                "attackVector": "NETWORK",
                "baseScore": 8.2,
                "baseSeverity": "HIGH",
                "privilegesRequired": "NONE",
                "subAvailabilityImpact": "NONE",
                "subConfidentialityImpact": "NONE",
                "subIntegrityImpact": "NONE",
                "userInteraction": "NONE",
                "vectorString": "CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N",
                "version": "4.0",
                "vulnAvailabilityImpact": "HIGH",
                "vulnConfidentialityImpact": "NONE",
                "vulnIntegrityImpact": "NONE"
              },
              "format": "CVSS"
            },
            {
              "cvssV3_1": {
                "attackComplexity": "HIGH",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 5.9,
                "baseSeverity": "MEDIUM",
                "confidentialityImpact": "NONE",
                "integrityImpact": "NONE",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H",
                "version": "3.1"
              },
              "format": "CVSS"
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-617",
                  "description": "Reachable Assertion",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-11-13T09:35:49.601Z",
            "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
            "shortName": "VulnCheck"
          },
          "references": [
            {
              "name": "GitHub Security Advisory (GHSA-5q78-j82c-2vr2)",
              "tags": [
                "vendor-advisory"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-5q78-j82c-2vr2"
            },
            {
              "name": "VulnCheck Advisory: vLLM 0.28.0 before 0.30.0 Denial of Service via Prompt Embeds on XD-RoPE Models",
              "tags": [
                "third-party-advisory"
              ],
              "url": "https://www.vulncheck.com/advisories/vllm-0.28.0-before-0.30.0-denial-of-service-via-prompt-embeds-on-xd-rope-models"
            }
          ],
          "title": "vLLM 0.28.0 before 0.30.0 Denial of Service via Prompt Embeds on XD-RoPE Models",
          "x_generator": {
            "engine": "vulncheck-endgame"
          }
        }
      },
      "cveMetadata": {
        "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "assignerShortName": "VulnCheck",
        "cveId": "CVE-2026-126398",
        "datePublished": "2026-11-13T09:35:49.601Z",
        "dateReserved": "2026-11-10T21:30:16.910Z",
        "dateUpdated": "2026-11-13T09:35:49.601Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-126399 (GCVE-0-2026-126399)

    Vulnerability from cvelistv5 – Published: 2026-11-13 09:35 – Updated: 2026-11-13 15:55
    VLAI
    Title
    vLLM 0.19.0 before 0.31.0 Resource Exhaustion via Request-Level num_frames
    Summary
    vLLM from 0.19.0 before 0.31.0 contains a resource exhaustion vulnerability that allows inference clients to bypass the server frame limit by setting media_io_kwargs.video.num_frames in chat completion requests. Attackers can supply num_frames=-1 or a large value with many base64 JPEG frames, forcing VideoMediaIO to decode all frames and np.stack them, causing memory exhaustion.
    SSVC
    Exploitation: none Automatable: no Technical Impact: partial
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-11-13 15:30 UTC
    CWE
    • CWE-770 - Allocation of Resources Without Limits or Throttling
    References
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: 0.19.0 , < 0.31.0 (semver)
    Unaffected: 0.31.0 (semver)
        cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
    Create a notification for this product.
    Date Public
    2026-10-27 00:00
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-126399",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-11-13T15:30:26.279127Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-11-13T15:55:11.981Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "defaultStatus": "unaffected",
              "packageURL": "pkg:pypi/vllm",
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "lessThan": "0.31.0",
                  "status": "affected",
                  "version": "0.19.0",
                  "versionType": "semver"
                },
                {
                  "status": "unaffected",
                  "version": "0.31.0",
                  "versionType": "semver"
                }
              ]
            }
          ],
          "cpeApplicability": [
            {
              "nodes": [
                {
                  "cpeMatch": [
                    {
                      "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
                      "versionEndExcluding": "0.31.0",
                      "versionStartIncluding": "0.19.0",
                      "vulnerable": true
                    }
                  ],
                  "negate": false,
                  "operator": "OR"
                }
              ]
            }
          ],
          "credits": [
            {
              "lang": "en",
              "type": "reporter",
              "value": "m4rgh"
            },
            {
              "lang": "en",
              "type": "coordinator",
              "value": "jperezdealgaba"
            }
          ],
          "datePublic": "2026-10-27T00:00:00.000Z",
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM from 0.19.0 before 0.31.0 contains a resource exhaustion vulnerability that allows inference clients to bypass the server frame limit by setting media_io_kwargs.video.num_frames in chat completion requests. Attackers can supply num_frames=-1 or a large value with many base64 JPEG frames, forcing VideoMediaIO to decode all frames and np.stack them, causing memory exhaustion."
            }
          ],
          "metrics": [
            {
              "cvssV4_0": {
                "attackComplexity": "LOW",
                "attackRequirements": "NONE",
                "attackVector": "NETWORK",
                "baseScore": 7.1,
                "baseSeverity": "HIGH",
                "privilegesRequired": "LOW",
                "subAvailabilityImpact": "NONE",
                "subConfidentialityImpact": "NONE",
                "subIntegrityImpact": "NONE",
                "userInteraction": "NONE",
                "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N",
                "version": "4.0",
                "vulnAvailabilityImpact": "HIGH",
                "vulnConfidentialityImpact": "NONE",
                "vulnIntegrityImpact": "NONE"
              },
              "format": "CVSS"
            },
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 6.5,
                "baseSeverity": "MEDIUM",
                "confidentialityImpact": "NONE",
                "integrityImpact": "NONE",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
                "version": "3.1"
              },
              "format": "CVSS"
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-770",
                  "description": "Allocation of Resources Without Limits or Throttling",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-11-13T09:35:48.994Z",
            "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
            "shortName": "VulnCheck"
          },
          "references": [
            {
              "name": "GitHub Security Advisory (GHSA-vxqj-p4gw-9h4c)",
              "tags": [
                "vendor-advisory"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-vxqj-p4gw-9h4c"
            },
            {
              "name": "VulnCheck Advisory: vLLM 0.19.0 before 0.31.0 Resource Exhaustion via Request-Level num_frames",
              "tags": [
                "third-party-advisory"
              ],
              "url": "https://www.vulncheck.com/advisories/vllm-0.19.0-before-0.31.0-resource-exhaustion-via-request-level-num-frames"
            }
          ],
          "title": "vLLM 0.19.0 before 0.31.0 Resource Exhaustion via Request-Level num_frames",
          "x_generator": {
            "engine": "vulncheck-endgame"
          }
        }
      },
      "cveMetadata": {
        "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "assignerShortName": "VulnCheck",
        "cveId": "CVE-2026-126399",
        "datePublished": "2026-11-13T09:35:48.994Z",
        "dateReserved": "2026-11-10T21:32:21.764Z",
        "dateUpdated": "2026-11-13T15:55:11.981Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-115918 (GCVE-0-2026-115918)

    Vulnerability from cvelistv5 – Published: 2026-10-26 17:21 – Updated: 2026-10-30 14:22
    VLAI
    Title
    vLLM: Responses API bypasses trust_request_chat_template for chat_template_kwargs
    Summary
    vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chat_template_kwargs[chat_template] when no server template is configured. ChatParams.get_apply_chat_template_kwargs() preserves that value without enforcing trust_request_chat_template, so the request can bypass the intended trust policy and cause CPU or memory exhaustion through Jinja rendering. This issue is fixed in version 0.32.0.
    SSVC
    Exploitation: none Automatable: no Technical Impact: partial
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-10-30 14:22 UTC
    CWE
    • CWE-400 - Uncontrolled Resource Consumption
    • CWE-770 - Allocation of Resources Without Limits or Throttling
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: >= 0.16.0, < 0.32.0
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-115918",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-10-30T14:22:12.561297Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-10-30T14:22:20.698Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 0.16.0, \u003c 0.32.0"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chat_template_kwargs[chat_template] when no server template is configured. ChatParams.get_apply_chat_template_kwargs() preserves that value without enforcing trust_request_chat_template, so the request can bypass the intended trust policy and cause CPU or memory exhaustion through Jinja rendering. This issue is fixed in version 0.32.0."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 6.5,
                "baseSeverity": "MEDIUM",
                "confidentialityImpact": "NONE",
                "integrityImpact": "NONE",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-400",
                  "description": "CWE-400: Uncontrolled Resource Consumption",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-770",
                  "description": "CWE-770: Allocation of Resources Without Limits or Throttling",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-10-26T17:21:49.719Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-x567-49g5-p4cf",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-x567-49g5-p4cf"
            },
            {
              "name": "https://github.com/vllm-project/vllm/pull/50300",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/pull/50300"
            },
            {
              "name": "https://github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134"
            },
            {
              "name": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"
            }
          ],
          "source": {
            "advisory": "GHSA-x567-49g5-p4cf",
            "discovery": "UNKNOWN"
          },
          "title": "vLLM: Responses API bypasses trust_request_chat_template for chat_template_kwargs"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-115918",
        "datePublished": "2026-10-26T17:21:49.719Z",
        "dateReserved": "2026-10-23T20:21:45.107Z",
        "dateUpdated": "2026-10-30T14:22:20.698Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-115917 (GCVE-0-2026-115917)

    Vulnerability from cvelistv5 – Published: 2026-10-26 17:20 – Updated: 2026-10-31 01:38
    VLAI
    Title
    vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server
    Summary
    vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the OpenAI-compatible server configures Starlette CORSMiddleware with allowed_origins set to a wildcard by default. A malicious web page can use a victim's browser to reach an unauthenticated vLLM server on localhost, an internal network, or a VPN, call endpoints including GET /v1/models and POST /v1/chat/completions, consume GPU resources, and read responses. Cookie-based cross-site request forgery does not apply because credentials are disabled by default, and deployments requiring bearer authentication are exposed only when the caller already has a usable token. This issue is fixed in version 0.32.0.
    SSVC
    Exploitation: none Automatable: no Technical Impact: partial
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-10-31 01:38 UTC
    CWE
    • CWE-942 - Permissive Cross-domain Policy with Untrusted Domains
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: < 0.32.0
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-115917",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-10-31T01:38:43.564283Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-10-31T01:38:53.155Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 0.32.0"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the OpenAI-compatible server configures Starlette CORSMiddleware with allowed_origins set to a wildcard by default. A malicious web page can use a victim\u0027s browser to reach an unauthenticated vLLM server on localhost, an internal network, or a VPN, call endpoints including GET /v1/models and POST /v1/chat/completions, consume GPU resources, and read responses. Cookie-based cross-site request forgery does not apply because credentials are disabled by default, and deployments requiring bearer authentication are exposed only when the caller already has a usable token. This issue is fixed in version 0.32.0."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "HIGH",
                "attackVector": "NETWORK",
                "availabilityImpact": "NONE",
                "baseScore": 3.4,
                "baseSeverity": "LOW",
                "confidentialityImpact": "LOW",
                "integrityImpact": "NONE",
                "privilegesRequired": "NONE",
                "scope": "CHANGED",
                "userInteraction": "REQUIRED",
                "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:L/I:N/A:N",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-942",
                  "description": "CWE-942: Permissive Cross-domain Policy with Untrusted Domains",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-10-26T17:20:09.065Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-vvpg-rrww-wpmh",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-vvpg-rrww-wpmh"
            },
            {
              "name": "https://github.com/vllm-project/vllm/pull/61009",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/pull/61009"
            },
            {
              "name": "https://github.com/vllm-project/vllm/commit/fcae5c98870ff2c20659731dce7ba3a3ff0d48aa",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/commit/fcae5c98870ff2c20659731dce7ba3a3ff0d48aa"
            },
            {
              "name": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"
            }
          ],
          "source": {
            "advisory": "GHSA-vvpg-rrww-wpmh",
            "discovery": "UNKNOWN"
          },
          "title": "vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-115917",
        "datePublished": "2026-10-26T17:20:09.065Z",
        "dateReserved": "2026-10-23T20:21:45.107Z",
        "dateUpdated": "2026-10-31T01:38:53.155Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-115916 (GCVE-0-2026-115916)

    Vulnerability from cvelistv5 – Published: 2026-10-26 17:18 – Updated: 2026-11-02 17:50
    VLAI
    Title
    vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)
    Summary
    vLLM is an inference and serving engine for large language models. Prior to 0.32.0, vllm/tokenizers/hf.py computes max_token_id with an off-by-one upper bound, allowing a pre-tokenized prompt ID equal to the vocabulary size to pass validation. For a tensor-parallel size of one and an exact multiple-of-64 vocabulary, VocabParallelEmbedding.forward does not mask that value before F.embedding uses it, causing a CUDA device-side assertion and terminating the engine. This issue is fixed in version 0.32.0.
    SSVC
    Exploitation: none Automatable: no Technical Impact: partial
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-11-02 17:49 UTC
    CWE
    • CWE-129 - Improper Validation of Array Index
    • CWE-193 - Off-by-one Error
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: < 0.32.0
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-115916",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-11-02T17:49:45.650631Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-11-02T17:50:28.478Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 0.32.0"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM is an inference and serving engine for large language models. Prior to 0.32.0, vllm/tokenizers/hf.py computes max_token_id with an off-by-one upper bound, allowing a pre-tokenized prompt ID equal to the vocabulary size to pass validation. For a tensor-parallel size of one and an exact multiple-of-64 vocabulary, VocabParallelEmbedding.forward does not mask that value before F.embedding uses it, causing a CUDA device-side assertion and terminating the engine. This issue is fixed in version 0.32.0."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 6.5,
                "baseSeverity": "MEDIUM",
                "confidentialityImpact": "NONE",
                "integrityImpact": "NONE",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-129",
                  "description": "CWE-129: Improper Validation of Array Index",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-193",
                  "description": "CWE-193: Off-by-one Error",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-10-26T17:18:17.582Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-q97c-p368-75c4",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-q97c-p368-75c4"
            },
            {
              "name": "https://github.com/vllm-project/vllm/pull/59491",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/pull/59491"
            },
            {
              "name": "https://github.com/vllm-project/vllm/commit/37cecc8141e2dcba9dd534897a164d4baaf27229",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/commit/37cecc8141e2dcba9dd534897a164d4baaf27229"
            },
            {
              "name": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"
            }
          ],
          "source": {
            "advisory": "GHSA-q97c-p368-75c4",
            "discovery": "UNKNOWN"
          },
          "title": "vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-115916",
        "datePublished": "2026-10-26T17:18:17.582Z",
        "dateReserved": "2026-10-23T20:21:45.107Z",
        "dateUpdated": "2026-11-02T17:50:28.478Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-115915 (GCVE-0-2026-115915)

    Vulnerability from cvelistv5 – Published: 2026-10-26 17:16 – Updated: 2026-10-26 19:35
    VLAI
    Title
    vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE
    Summary
    vLLM is an inference and serving engine for large language models. Prior to 0.32.0, ImageMediaIO passes attacker-controlled image bytes to Pillow through Image.open(BytesIO(data)) without restricting decoder selection, and the MIME label does not constrain the selected format. Image-capable request paths through parse_image() and fetch_image() can therefore dispatch an EPS payload to host components. A host with Ghostscript affected by CVE-2024-29510 can execute commands with the vLLM process's privileges, while environments using Pillow 12.0.0 through 12.2.0 can trigger CVE-2026-59203 and exhaust media-loading workers. Deployments without the applicable vulnerable dependency are not affected by that corresponding impact. This issue is fixed in version 0.32.0.
    SSVC
    Exploitation: none Automatable: no Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-10-26 19:31 UTC
    CWE
    • CWE-20 - Improper Input Validation
    • CWE-183 - Permissive List of Allowed Inputs
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: < 0.32.0
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-115915",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-10-26T19:31:21.498549Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-10-26T19:35:10.423Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 0.32.0"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM is an inference and serving engine for large language models. Prior to 0.32.0, ImageMediaIO passes attacker-controlled image bytes to Pillow through Image.open(BytesIO(data)) without restricting decoder selection, and the MIME label does not constrain the selected format. Image-capable request paths through parse_image() and fetch_image() can therefore dispatch an EPS payload to host components. A host with Ghostscript affected by CVE-2024-29510 can execute commands with the vLLM process\u0027s privileges, while environments using Pillow 12.0.0 through 12.2.0 can trigger CVE-2026-59203 and exhaust media-loading workers. Deployments without the applicable vulnerable dependency are not affected by that corresponding impact. This issue is fixed in version 0.32.0."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "HIGH",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 8.1,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-20",
                  "description": "CWE-20: Improper Input Validation",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-183",
                  "description": "CWE-183: Permissive List of Allowed Inputs",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-10-26T17:16:57.526Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-h3rc-j82p-2c3h",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-h3rc-j82p-2c3h"
            },
            {
              "name": "https://github.com/vllm-project/vllm/pull/60022",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/pull/60022"
            },
            {
              "name": "https://github.com/vllm-project/vllm/commit/710ac56e691d4713feca50a43e6c440f07d373fd",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/commit/710ac56e691d4713feca50a43e6c440f07d373fd"
            },
            {
              "name": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"
            }
          ],
          "source": {
            "advisory": "GHSA-h3rc-j82p-2c3h",
            "discovery": "UNKNOWN"
          },
          "title": "vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-115915",
        "datePublished": "2026-10-26T17:16:06.387Z",
        "dateReserved": "2026-10-23T20:21:45.107Z",
        "dateUpdated": "2026-10-26T19:35:10.423Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-115914 (GCVE-0-2026-115914)

    Vulnerability from cvelistv5 – Published: 2026-10-26 17:08 – Updated: 2026-10-30 14:23
    VLAI
    Title
    vLLM DeepSeek-OCR image processing vulnerable to denial of service
    Summary
    vLLM is an inference and serving engine for large language models. From 0.11.1 until 0.32.0, the DeepSeek-OCR, DeepSeek-OCR-2, and Unlimited-OCR image path allows a remote client that can reach the OpenAI-compatible API to submit a legal image whose normalized pixels sum to zero when that image is alone in its per-step encoder batch. _parse_and_validate_image_input returns no embedding, embed_multimodal propagates that value, and sanity_check_mm_encoder_outputs triggers a fatal assertion that shuts down the engine for all users. This issue is fixed in version 0.32.0.
    SSVC
    Exploitation: none Automatable: no Technical Impact: partial
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-10-30 14:23 UTC
    CWE
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: >= 0.11.1, < 0.32.0
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-115914",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-10-30T14:23:13.354875Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-10-30T14:23:21.521Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 0.11.1, \u003c 0.32.0"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM is an inference and serving engine for large language models. From 0.11.1 until 0.32.0, the DeepSeek-OCR, DeepSeek-OCR-2, and Unlimited-OCR image path allows a remote client that can reach the OpenAI-compatible API to submit a legal image whose normalized pixels sum to zero when that image is alone in its per-step encoder batch. _parse_and_validate_image_input returns no embedding, embed_multimodal propagates that value, and sanity_check_mm_encoder_outputs triggers a fatal assertion that shuts down the engine for all users. This issue is fixed in version 0.32.0."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 6.5,
                "baseSeverity": "MEDIUM",
                "confidentialityImpact": "NONE",
                "integrityImpact": "NONE",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-617",
                  "description": "CWE-617: Reachable Assertion",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-10-26T17:08:20.839Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-gq5q-89c7-vhvx",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-gq5q-89c7-vhvx"
            },
            {
              "name": "https://github.com/vllm-project/vllm/pull/59417",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/pull/59417"
            },
            {
              "name": "https://github.com/vllm-project/vllm/commit/c15672cfb49152ebf65cfd188e71b84593ec5686",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/commit/c15672cfb49152ebf65cfd188e71b84593ec5686"
            },
            {
              "name": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"
            }
          ],
          "source": {
            "advisory": "GHSA-gq5q-89c7-vhvx",
            "discovery": "UNKNOWN"
          },
          "title": "vLLM DeepSeek-OCR image processing vulnerable to denial of service"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-115914",
        "datePublished": "2026-10-26T17:08:20.839Z",
        "dateReserved": "2026-10-23T20:21:45.107Z",
        "dateUpdated": "2026-10-30T14:23:21.521Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-115913 (GCVE-0-2026-115913)

    Vulnerability from cvelistv5 – Published: 2026-10-26 16:56 – Updated: 2026-11-02 17:48
    VLAI
    Title
    vLLM: Phi-4 multimodal audio encoder materializes and retains full attention matrices: a single max-length audio OOM-crashes the vLLM engine
    Summary
    vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the Phi-4 multimodal audio encoder in phi4mm_audio.py and phi4mm_utils.py uses eager attention by default, allowing a remote client to submit one legal long audio clip that causes MultiHeadedAttention.forward_attention to materialize and retain full attention matrices in self.attn. The scaled dot-product attention branch does not materialize these matrices. The resulting quadratic GPU-memory use can cause an out-of-memory condition and terminate EngineCore for all users. This issue is fixed in version 0.32.0.
    SSVC
    Exploitation: none Automatable: no Technical Impact: partial
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-11-02 17:48 UTC
    CWE
    • CWE-770 - Allocation of Resources Without Limits or Throttling
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: < 0.32.0
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-115913",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-11-02T17:48:03.108418Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-11-02T17:48:14.216Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 0.32.0"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the Phi-4 multimodal audio encoder in phi4mm_audio.py and phi4mm_utils.py uses eager attention by default, allowing a remote client to submit one legal long audio clip that causes MultiHeadedAttention.forward_attention to materialize and retain full attention matrices in self.attn. The scaled dot-product attention branch does not materialize these matrices. The resulting quadratic GPU-memory use can cause an out-of-memory condition and terminate EngineCore for all users. This issue is fixed in version 0.32.0."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 6.5,
                "baseSeverity": "MEDIUM",
                "confidentialityImpact": "NONE",
                "integrityImpact": "NONE",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-770",
                  "description": "CWE-770: Allocation of Resources Without Limits or Throttling",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-10-26T16:56:59.817Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8397-8qf6-f2gm",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8397-8qf6-f2gm"
            },
            {
              "name": "https://github.com/vllm-project/vllm/pull/60614",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/pull/60614"
            },
            {
              "name": "https://github.com/vllm-project/vllm/commit/3d52578e13454de0bb8352cac988347cdcc89928",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/commit/3d52578e13454de0bb8352cac988347cdcc89928"
            },
            {
              "name": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"
            }
          ],
          "source": {
            "advisory": "GHSA-8397-8qf6-f2gm",
            "discovery": "UNKNOWN"
          },
          "title": "vLLM: Phi-4 multimodal audio encoder materializes and retains full attention matrices: a single max-length audio OOM-crashes the vLLM engine"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-115913",
        "datePublished": "2026-10-26T16:56:59.817Z",
        "dateReserved": "2026-10-23T20:21:45.107Z",
        "dateUpdated": "2026-11-02T17:48:14.216Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-115912 (GCVE-0-2026-115912)

    Vulnerability from cvelistv5 – Published: 2026-10-26 16:54 – Updated: 2026-10-26 19:35
    VLAI
    Title
    vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled
    Summary
    vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonic_id values in public multimodal features.kwargs_data. In scale-out deployments with shared-memory multimodal caching enabled, workers trust those values and pass attacker-selected bytes to pickle.loads(), allowing arbitrary Python execution even when insecure serialization is disabled. This issue is fixed in version 0.32.0.
    SSVC
    Exploitation: none Automatable: no Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-10-26 19:31 UTC
    CWE
    • CWE-502 - Deserialization of Untrusted Data
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: < 0.32.0
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-115912",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-10-26T19:31:18.550495Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-10-26T19:35:42.879Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 0.32.0"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonic_id values in public multimodal features.kwargs_data. In scale-out deployments with shared-memory multimodal caching enabled, workers trust those values and pass attacker-selected bytes to pickle.loads(), allowing arbitrary Python execution even when insecure serialization is disabled. This issue is fixed in version 0.32.0."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "HIGH",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 7.5,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-502",
                  "description": "CWE-502: Deserialization of Untrusted Data",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-10-26T16:54:00.643Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-6757-hggm-hp2w",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-6757-hggm-hp2w"
            },
            {
              "name": "https://github.com/vllm-project/vllm/pull/59357",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/pull/59357"
            },
            {
              "name": "https://github.com/vllm-project/vllm/commit/3d5625cc3c2474994107047d7a6ecb8e4008f9b0",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/commit/3d5625cc3c2474994107047d7a6ecb8e4008f9b0"
            },
            {
              "name": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"
            }
          ],
          "source": {
            "advisory": "GHSA-6757-hggm-hp2w",
            "discovery": "UNKNOWN"
          },
          "title": "vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-115912",
        "datePublished": "2026-10-26T16:54:00.643Z",
        "dateReserved": "2026-10-23T20:21:45.107Z",
        "dateUpdated": "2026-10-26T19:35:42.879Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-115911 (GCVE-0-2026-115911)

    Vulnerability from cvelistv5 – Published: 2026-10-26 16:47 – Updated: 2026-10-30 14:20
    VLAI
    Title
    vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool
    Summary
    vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.32.0, authenticated callers can supply a request chat template when no server-side --chat-template is configured, or a malicious model repository can provide a template that is compiled and rendered by tokenizer.apply_chat_template() without a wall-clock timeout, output-size limit, or iteration bound. Rendering runs in a ThreadPoolExecutor with one worker by default, so a nonterminating render can block /v1/responses and other chat-template users after the request ends, while an output-expanding render can exhaust server memory. Harmony models are not affected because they do not use this Jinja path. This issue is fixed in version 0.32.0.
    SSVC
    Exploitation: none Automatable: no Technical Impact: partial
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-10-30 14:20 UTC
    CWE
    • CWE-400 - Uncontrolled Resource Consumption
    • CWE-770 - Allocation of Resources Without Limits or Throttling
    • CWE-834 - Excessive Iteration
    Impacted products
    Vendor Product Version
    vllm-project vllm Affected: >= 0.19.0, < 0.32.0
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-115911",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-10-30T14:20:35.704686Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-10-30T14:20:51.484Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 0.19.0, \u003c 0.32.0"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.32.0, authenticated callers can supply a request chat template when no server-side --chat-template is configured, or a malicious model repository can provide a template that is compiled and rendered by tokenizer.apply_chat_template() without a wall-clock timeout, output-size limit, or iteration bound. Rendering runs in a ThreadPoolExecutor with one worker by default, so a nonterminating render can block /v1/responses and other chat-template users after the request ends, while an output-expanding render can exhaust server memory. Harmony models are not affected because they do not use this Jinja path. This issue is fixed in version 0.32.0."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 6.5,
                "baseSeverity": "MEDIUM",
                "confidentialityImpact": "NONE",
                "integrityImpact": "NONE",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-400",
                  "description": "CWE-400: Uncontrolled Resource Consumption",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-770",
                  "description": "CWE-770: Allocation of Resources Without Limits or Throttling",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-834",
                  "description": "CWE-834: Excessive Iteration",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-10-26T16:47:59.377Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-542m-9234-8gvf",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-542m-9234-8gvf"
            },
            {
              "name": "https://github.com/vllm-project/vllm/pull/50300",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/pull/50300"
            },
            {
              "name": "https://github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134"
            },
            {
              "name": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"
            }
          ],
          "source": {
            "advisory": "GHSA-542m-9234-8gvf",
            "discovery": "UNKNOWN"
          },
          "title": "vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-115911",
        "datePublished": "2026-10-26T16:47:59.377Z",
        "dateReserved": "2026-10-23T20:21:45.107Z",
        "dateUpdated": "2026-10-30T14:20:51.484Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }