CVE-2026-44222 (GCVE-0-2026-44222)

Vulnerability from cvelistv5 – Published: 2026-05-12 19:57 – Updated: 2026-05-13 12:24
VLAI
Title
vLLM: Remote DoS via Special-Token Placeholders
Summary
vLLM is an inference and serving engine for large language models (LLMs). From 0.6.1 to before 0.20.0, there is a a Token Injection vulnerability in vLLM’s multimodal processing. Unauthenticated, text-only prompts that spell special tokens are interpreted as control. Image and video placeholder sequences supplied without matching data cause vLLM to index into empty grids during input-position computation, raising an unhandled IndexError and terminating the worker or degrading availability. Multimodal paths that rely on image_grid_thw/video_grid_thw are affected. This vulnerability is fixed in 0.20.0.
SSVC
Exploitation: none Automatable: no Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-05-13 12:24 UTC
CWE
  • CWE-129 - Improper Validation of Array Index
References
Impacted products
Vendor Product Version
vllm-project vllm Affected: >= 0.6.1, < 0.20.0
Create a notification for this product.
Show details on NVD website

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-44222",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-05-13T12:24:39.409933Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-05-13T12:24:53.560Z",
          "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= 0.6.1, \u003c 0.20.0"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "vLLM is an inference and serving engine for large language models (LLMs). From 0.6.1 to before 0.20.0, there is a a Token Injection vulnerability in vLLM\u2019s multimodal processing. Unauthenticated, text-only prompts that spell special tokens are interpreted as control. Image and video placeholder sequences supplied without matching data cause vLLM to index into empty grids during input-position computation, raising an unhandled IndexError and terminating the worker or degrading availability. Multimodal paths that rely on image_grid_thw/video_grid_thw are affected. This vulnerability is fixed in 0.20.0."
        }
      ],
      "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"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-05-12T19:57:25.336Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-hpv8-x276-m59f",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-hpv8-x276-m59f"
        },
        {
          "name": "https://github.com/vllm-project/vllm/issues/32656",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/issues/32656"
        }
      ],
      "source": {
        "advisory": "GHSA-hpv8-x276-m59f",
        "discovery": "UNKNOWN"
      },
      "title": "vLLM: Remote DoS via Special-Token Placeholders"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-44222",
    "datePublished": "2026-05-12T19:57:25.336Z",
    "dateReserved": "2026-05-05T15:42:40.518Z",
    "dateUpdated": "2026-05-13T12:24:53.560Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-44222",
      "date": "2026-11-16",
      "epss": "0.00414",
      "percentile": "0.3623"
    },
    "nvd": {
      "cve": {
        "affected": [
          {
            "affectedData": [
              {
                "product": "vllm",
                "vendor": "vllm-project",
                "versions": [
                  {
                    "status": "affected",
                    "version": "\u003e= 0.6.1, \u003c 0.20.0"
                  }
                ]
              }
            ],
            "source": "security-advisories@github.com"
          }
        ],
        "configurations": [
          {
            "nodes": [
              {
                "cpeMatch": [
                  {
                    "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
                    "matchCriteriaId": "7360938D-E6DB-48BB-BE23-15CD63FD3956",
                    "versionEndExcluding": "0.20.0",
                    "versionStartIncluding": "0.6.1",
                    "vulnerable": true
                  }
                ],
                "negate": false,
                "operator": "OR"
              }
            ]
          }
        ],
        "cveTags": [],
        "descriptions": [
          {
            "lang": "en",
            "value": "vLLM is an inference and serving engine for large language models (LLMs). From 0.6.1 to before 0.20.0, there is a a Token Injection vulnerability in vLLM\u2019s multimodal processing. Unauthenticated, text-only prompts that spell special tokens are interpreted as control. Image and video placeholder sequences supplied without matching data cause vLLM to index into empty grids during input-position computation, raising an unhandled IndexError and terminating the worker or degrading availability. Multimodal paths that rely on image_grid_thw/video_grid_thw are affected. This vulnerability is fixed in 0.20.0."
          },
          {
            "lang": "es",
            "value": "vLLM es un motor de inferencia y servicio para modelos de lenguaje grandes (LLM). Desde la versi\u00f3n 0.6.1 hasta antes de la 0.20.0, existe una vulnerabilidad de inyecci\u00f3n de tokens en el procesamiento multimodal de vLLM. Las indicaciones no autenticadas y solo de texto que deletrean tokens especiales se interpretan como control. Las secuencias de marcadores de posici\u00f3n de imagen y video suministradas sin datos coincidentes hacen que vLLM indexe en cuadr\u00edculas vac\u00edas durante el c\u00e1lculo de la posici\u00f3n de entrada, lo que provoca un IndexError no manejado y termina el proceso de trabajo o degrada la disponibilidad. Las rutas multimodales que dependen de image_grid_thw/video_grid_thw se ven afectadas. Esta vulnerabilidad se corrigi\u00f3 en la versi\u00f3n 0.20.0."
          }
        ],
        "id": "CVE-2026-44222",
        "lastModified": "2026-11-11T20:10:00.273",
        "metrics": {
          "cvssMetricV31": [
            {
              "cvssData": {
                "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"
              },
              "exploitabilityScore": 2.8,
              "impactScore": 3.6,
              "source": "security-advisories@github.com",
              "type": "Secondary"
            },
            {
              "cvssData": {
                "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"
              },
              "exploitabilityScore": 3.9,
              "impactScore": 3.6,
              "source": "nvd@nist.gov",
              "type": "Primary"
            }
          ],
          "ssvcV203": [
            {
              "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "ssvcData": {
                "id": "CVE-2026-44222",
                "options": [
                  {
                    "exploitation": "none"
                  },
                  {
                    "automatable": "no"
                  },
                  {
                    "technicalImpact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-05-13T12:24:39.409933Z",
                "version": "2.0.3"
              }
            }
          ]
        },
        "published": "2026-05-12T20:16:43.160",
        "references": [
          {
            "source": "security-advisories@github.com",
            "tags": [
              "Issue Tracking"
            ],
            "url": "https://github.com/vllm-project/vllm/issues/32656"
          },
          {
            "source": "security-advisories@github.com",
            "tags": [
              "Exploit",
              "Vendor Advisory"
            ],
            "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-hpv8-x276-m59f"
          }
        ],
        "sourceIdentifier": "security-advisories@github.com",
        "vulnStatus": "Analyzed",
        "weaknesses": [
          {
            "description": [
              {
                "lang": "en",
                "value": "CWE-129"
              }
            ],
            "source": "security-advisories@github.com",
            "type": "Secondary"
          }
        ]
      }
    },
    "redhat_vex": {
      "aggregate_severity": "Important",
      "current_release_date": "2026-10-02T19:19:13+00:00",
      "cve": "CVE-2026-44222",
      "id": "CVE-2026-44222",
      "initial_release_date": "2026-05-12T19:57:25.336000+00:00",
      "product_status:fixed": "6",
      "product_status:known_affected": "12",
      "product_status:known_not_affected": "4",
      "source": "Red Hat CSAF VEX",
      "status": "final",
      "title": "vllm: vLLM: Denial of Service via malformed multimodal input or token injection",
      "url": "https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-44222.json",
      "version": "3"
    },
    "vulnrichment": {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-44222",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-05-13T12:24:39.409933Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-05-13T12:24:49.160Z",
              "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= 0.6.1, \u003c 0.20.0"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM is an inference and serving engine for large language models (LLMs). From 0.6.1 to before 0.20.0, there is a a Token Injection vulnerability in vLLM\u2019s multimodal processing. Unauthenticated, text-only prompts that spell special tokens are interpreted as control. Image and video placeholder sequences supplied without matching data cause vLLM to index into empty grids during input-position computation, raising an unhandled IndexError and terminating the worker or degrading availability. Multimodal paths that rely on image_grid_thw/video_grid_thw are affected. This vulnerability is fixed in 0.20.0."
            }
          ],
          "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"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-05-12T19:57:25.336Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-hpv8-x276-m59f",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-hpv8-x276-m59f"
            },
            {
              "name": "https://github.com/vllm-project/vllm/issues/32656",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/issues/32656"
            }
          ],
          "source": {
            "advisory": "GHSA-hpv8-x276-m59f",
            "discovery": "UNKNOWN"
          },
          "title": "vLLM: Remote DoS via Special-Token Placeholders"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-44222",
        "datePublished": "2026-05-12T19:57:25.336Z",
        "dateReserved": "2026-05-05T15:42:40.518Z",
        "dateUpdated": "2026-05-13T12:24:53.560Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.


Loading…

Loading…

Loading…

Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.

Sightings

Author Source Type Date Other

Nomenclature

  • Seen: The vulnerability was mentioned, discussed, or observed by the user.
  • Confirmed: The vulnerability has been validated from an analyst's perspective.
  • Published Proof of Concept: A public proof of concept is available for this vulnerability.
  • Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
  • Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
  • Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
  • Not confirmed: The user expressed doubt about the validity of the vulnerability.
  • Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.

Loading…

Loading…

Loading…

Related by attack behaviour

Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.


Loading…