Vulnerability-Lookup

PYSEC-2025-43

Vulnerability from pysec - Published: 2025-05-29 17:15 - Updated: 2025-05-29 19:21

Details

vLLM is an inference and serving engine for large language models (LLMs). In versions starting from 0.7.0 to before 0.9.0, in the file vllm/multimodal/hasher.py, the MultiModalHasher class has a security and data integrity issue in its image hashing method. Currently, it serializes PIL.Image.Image objects using only obj.tobytes(), which returns only the raw pixel data, without including metadata such as the image’s shape (width, height, mode). As a result, two images of different sizes (e.g., 30x100 and 100x30) with the same pixel byte sequence could generate the same hash value. This may lead to hash collisions, incorrect cache hits, and even data leakage or security risks. This issue has been patched in version 0.9.0.

Impacted products

Name	purl
vllm	pkg:pypi/vllm

Aliases

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "vllm",
        "purl": "pkg:pypi/vllm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "99404f53c72965b41558aceb1bc2380875f5d848"
            }
          ],
          "repo": "https://github.com/vllm-project/vllm",
          "type": "GIT"
        },
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.9.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ],
      "versions": [
        "0.0.1",
        "0.1.0",
        "0.1.1",
        "0.1.2",
        "0.1.3",
        "0.1.4",
        "0.1.5",
        "0.1.6",
        "0.1.7",
        "0.2.0",
        "0.2.1",
        "0.2.1.post1",
        "0.2.2",
        "0.2.3",
        "0.2.4",
        "0.2.5",
        "0.2.6",
        "0.2.7",
        "0.3.0",
        "0.3.1",
        "0.3.2",
        "0.3.3",
        "0.4.0",
        "0.4.0.post1",
        "0.4.1",
        "0.4.2",
        "0.4.3",
        "0.5.0",
        "0.5.0.post1",
        "0.5.1",
        "0.5.2",
        "0.5.3",
        "0.5.3.post1",
        "0.5.4",
        "0.5.5",
        "0.6.0",
        "0.6.1",
        "0.6.1.post1",
        "0.6.1.post2",
        "0.6.2",
        "0.6.3",
        "0.6.3.post1",
        "0.6.4",
        "0.6.4.post1",
        "0.6.5",
        "0.6.6",
        "0.6.6.post1",
        "0.7.0",
        "0.7.1",
        "0.7.2",
        "0.7.3",
        "0.8.0",
        "0.8.1",
        "0.8.2",
        "0.8.3",
        "0.8.4",
        "0.8.5",
        "0.8.5.post1"
      ]
    }
  ],
  "aliases": [
    "CVE-2025-46722",
    "GHSA-c65p-x677-fgj6"
  ],
  "details": "vLLM is an inference and serving engine for large language models (LLMs). In versions starting from 0.7.0 to before 0.9.0, in the file vllm/multimodal/hasher.py, the MultiModalHasher class has a security and data integrity issue in its image hashing method. Currently, it serializes PIL.Image.Image objects using only obj.tobytes(), which returns only the raw pixel data, without including metadata such as the image\u2019s shape (width, height, mode). As a result, two images of different sizes (e.g., 30x100 and 100x30) with the same pixel byte sequence could generate the same hash value. This may lead to hash collisions, incorrect cache hits, and even data leakage or security risks. This issue has been patched in version 0.9.0.",
  "id": "PYSEC-2025-43",
  "modified": "2025-05-29T19:21:01.611587+00:00",
  "published": "2025-05-29T17:15:21+00:00",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-c65p-x677-fgj6"
    },
    {
      "type": "FIX",
      "url": "https://github.com/vllm-project/vllm/commit/99404f53c72965b41558aceb1bc2380875f5d848"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/pull/17378"
    }
  ]
}

CVE-2025-46722 (GCVE-0-2025-46722)

Vulnerability from cvelistv5 – Published: 2025-05-29 16:36 – Updated: 2025-05-29 18:13

Title

vLLM has a Weakness in MultiModalHasher Image Hashing Implementation

Summary

Severity

4.2 (Medium)


                        
                          CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:L/I:N/A:L

SSVC

Exploitation: none Automatable: no Technical Impact: partial

CISA Coordinator · CISA-ADP (v2.0.3)

Decision recorded 2025-05-29 18:12 UTC

CWE

CWE-1288 - Improper Validation of Consistency within Input
CWE-1023 - Incomplete Comparison with Missing Factors

Assigner

GitHub_M mitre root Scorecard

References

3 references

URL	Tags
https://github.com/vllm-project/vllm/security/adv…	x_refsource_CONFIRM
https://github.com/vllm-project/vllm/pull/17378	x_refsource_MISC
https://github.com/vllm-project/vllm/commit/99404…	x_refsource_MISC

Impacted products

1 product

Vendor	Product	Version
vllm-project	vllm	Affected: >= 0.7.0, < 0.9.0

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2025-46722",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2025-05-29T18:12:29.713264Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2025-05-29T18:13:02.824Z",
          "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= 0.7.0, \u003c 0.9.0"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "vLLM is an inference and serving engine for large language models (LLMs). In versions starting from 0.7.0 to before 0.9.0, in the file vllm/multimodal/hasher.py, the MultiModalHasher class has a security and data integrity issue in its image hashing method. Currently, it serializes PIL.Image.Image objects using only obj.tobytes(), which returns only the raw pixel data, without including metadata such as the image\u2019s shape (width, height, mode). As a result, two images of different sizes (e.g., 30x100 and 100x30) with the same pixel byte sequence could generate the same hash value. This may lead to hash collisions, incorrect cache hits, and even data leakage or security risks. This issue has been patched in version 0.9.0."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "HIGH",
            "attackVector": "NETWORK",
            "availabilityImpact": "LOW",
            "baseScore": 4.2,
            "baseSeverity": "MEDIUM",
            "confidentialityImpact": "LOW",
            "integrityImpact": "NONE",
            "privilegesRequired": "LOW",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:L/I:N/A:L",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-1288",
              "description": "CWE-1288: Improper Validation of Consistency within Input",
              "lang": "en",
              "type": "CWE"
            }
          ]
        },
        {
          "descriptions": [
            {
              "cweId": "CWE-1023",
              "description": "CWE-1023: Incomplete Comparison with Missing Factors",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2025-05-29T16:36:12.879Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-c65p-x677-fgj6",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-c65p-x677-fgj6"
        },
        {
          "name": "https://github.com/vllm-project/vllm/pull/17378",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/pull/17378"
        },
        {
          "name": "https://github.com/vllm-project/vllm/commit/99404f53c72965b41558aceb1bc2380875f5d848",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/commit/99404f53c72965b41558aceb1bc2380875f5d848"
        }
      ],
      "source": {
        "advisory": "GHSA-c65p-x677-fgj6",
        "discovery": "UNKNOWN"
      },
      "title": "vLLM has a Weakness in MultiModalHasher Image Hashing Implementation"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2025-46722",
    "datePublished": "2025-05-29T16:36:12.879Z",
    "dateReserved": "2025-04-28T20:56:09.084Z",
    "dateUpdated": "2025-05-29T18:13:02.824Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.1"
}

GHSA-C65P-X677-FGJ6

Vulnerability from github – Published: 2025-05-28 18:03 – Updated: 2025-05-29 21:36

Summary

vLLM has a Weakness in MultiModalHasher Image Hashing Implementation

Details

Summary

In the file vllm/multimodal/hasher.py, the MultiModalHasher class has a security and data integrity issue in its image hashing method. Currently, it serializes PIL.Image.Image objects using only obj.tobytes(), which returns only the raw pixel data, without including metadata such as the image’s shape (width, height, mode). As a result, two images of different sizes (e.g., 30x100 and 100x30) with the same pixel byte sequence could generate the same hash value. This may lead to hash collisions, incorrect cache hits, and even data leakage or security risks.

Details

Affected file: vllm/multimodal/hasher.py
Affected method: MultiModalHasher.serialize_item https://github.com/vllm-project/vllm/blob/9420a1fc30af1a632bbc2c66eb8668f3af41f026/vllm/multimodal/hasher.py#L34-L35
Current behavior: For Image.Image instances, only obj.tobytes() is used for hashing.
Problem description: obj.tobytes() does not include the image’s width, height, or mode metadata.
Impact: Two images with the same pixel byte sequence but different sizes could be regarded as the same image by the cache and hashing system, which may result in:
- Incorrect cache hits, leading to abnormal responses
- Deliberate construction of images with different meanings but the same hash value

Recommendation

In the serialize_item method, serialization of Image.Image objects should include not only pixel data, but also all critical metadata—such as dimensions (size), color mode (mode), format, and especially the info dictionary. The info dictionary is particularly important in palette-based images (e.g., mode 'P'), where the palette itself is stored in info. Ignoring info can result in hash collisions between visually distinct images with the same pixel bytes but different palettes or metadata. This can lead to incorrect cache hits or even data leakage.

Summary:
Serializing only the raw pixel data is insecure. Always include all image metadata (size, mode, format, info) in the hash calculation to prevent collisions, especially in cases like palette-based images.

Impact for other modalities For the influence of other modalities, since the video modality is transformed into a multi-dimensional array containing the length, width, time, etc. of the video, the same problem exists due to the incorrect sequence of numpy as well.

For audio, since the momo function is not enabled in librosa.load, the loaded audio is automatically encoded into single channels by librosa and returns a one-dimensional array of numpy, thus keeping the structure of numpy fixed and not affected by this issue.

Fixes

https://github.com/vllm-project/vllm/pull/17378

Severity

4.2 (Medium)


                  
                    CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:L/I:N/A:L

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "vllm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0.7.0"
            },
            {
              "fixed": "0.9.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2025-46722"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-1023",
      "CWE-1288"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2025-05-28T18:03:41Z",
    "nvd_published_at": "2025-05-29T17:15:21Z",
    "severity": "MODERATE"
  },
  "details": "## Summary\n\nIn the file `vllm/multimodal/hasher.py`, the `MultiModalHasher` class has a security and data integrity issue in its image hashing method. Currently, it serializes `PIL.Image.Image` objects using only `obj.tobytes()`, which returns only the raw pixel data, without including metadata such as the image\u2019s shape (width, height, mode). As a result, two images of different sizes (e.g., 30x100 and 100x30) with the same pixel byte sequence could generate the same hash value. This may lead to hash collisions, incorrect cache hits, and even data leakage or security risks.\n\n## Details\n\n- **Affected file:** `vllm/multimodal/hasher.py`\n- **Affected method:** `MultiModalHasher.serialize_item`\nhttps://github.com/vllm-project/vllm/blob/9420a1fc30af1a632bbc2c66eb8668f3af41f026/vllm/multimodal/hasher.py#L34-L35\n- **Current behavior:** For `Image.Image` instances, only `obj.tobytes()` is used for hashing.\n- **Problem description:** `obj.tobytes()` does not include the image\u2019s width, height, or mode metadata.\n- **Impact:** Two images with the same pixel byte sequence but different sizes could be regarded as the same image by the cache and hashing system, which may result in:\n    - Incorrect cache hits, leading to abnormal responses\n    - Deliberate construction of images with different meanings but the same hash value\n\n\n## Recommendation\n\nIn the `serialize_item` method, **serialization of `Image.Image` objects should include not only pixel data, but also all critical metadata**\u2014such as dimensions (`size`), color mode (`mode`), format, and especially the `info` dictionary. The `info` dictionary is particularly important in palette-based images (e.g., mode `\u0027P\u0027`), where the palette itself is stored in `info`. Ignoring `info` can result in hash collisions between visually distinct images with the same pixel bytes but different palettes or metadata. This can lead to incorrect cache hits or even data leakage.\n\n**Summary:**  \nSerializing only the raw pixel data is insecure. Always include all image metadata (`size`, `mode`, `format`, `info`) in the hash calculation to prevent collisions, especially in cases like palette-based images.\n\n**Impact for other modalities**\nFor the influence of other modalities, since the video modality is transformed into a multi-dimensional array containing the length, width, time, etc. of the video, the same problem exists due to the incorrect sequence of numpy as well.\n\nFor audio, since the momo function is not enabled in librosa.load, the loaded audio is automatically encoded into single channels by librosa and returns a one-dimensional array of numpy, thus keeping the structure of numpy fixed and not affected by this issue.\n\n## Fixes\n\n* https://github.com/vllm-project/vllm/pull/17378",
  "id": "GHSA-c65p-x677-fgj6",
  "modified": "2025-05-29T21:36:24Z",
  "published": "2025-05-28T18:03:41Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-c65p-x677-fgj6"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2025-46722"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/pull/17378"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/commit/99404f53c72965b41558aceb1bc2380875f5d848"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2025-43.yaml"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/vllm-project/vllm"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:L/I:N/A:L",
      "type": "CVSS_V3"
    }
  ],
  "summary": "vLLM has a Weakness in MultiModalHasher Image Hashing Implementation"
}

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.

The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base model, served locally by ML-Gateway. They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.

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.

Action not permitted

PYSEC-2025-43

CVE-2025-46722 (GCVE-0-2025-46722)

GHSA-C65P-X677-FGJ6

Summary

Details

Recommendation

Fixes

Tags

Sightings

Nomenclature

Related by attack behaviour