Vulnerability-Lookup

PYSEC-2026-2019

Vulnerability from pysec - Published: 2026-07-07 16:03 - Updated: 2026-07-07 17:25

Details

Summary

Users can crash the vLLM engine serving multimodal models by passing multimodal embedding inputs with correct ndim but incorrect shape (e.g. hidden dimension is wrong), regardless of whether the model is intended to support such inputs (as defined in the Supported Models page).

The issue has existed ever since we added support for image embedding inputs, i.e. #6613 (released in v0.5.5)

Details

Using image embeddings as an example:

For models that support image embedding inputs, the engine crashes when scattering the embeddings to inputs_embeds (mismatched shape)
For models that don't support image embedding inputs, the engine crashes when validating the inputs inside get_input_embeddings (validation fails).

This happens because we only validate ndim of the tensor, but not the full shape, in input processor (via MultiModalDataParser).

Impact

Denial of service by crashing the engine

Mitigation

Use API key to limit access to trusted users.
Set --limit-mm-per-prompt to 0 for all non-text modalities to ban multimodal inputs, which includes multimodal embedding inputs. However, the model would then only accept text, defeating the purpose of using a multi-modal model.

Resolution

https://github.com/vllm-project/vllm/pull/27204

Severity

6.5 (Medium)


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

8.3 (High)


                  
                    CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:H

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": "0.5.5"
            },
            {
              "fixed": "0.11.1"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ],
      "versions": [
        "0.10.0",
        "0.10.1",
        "0.10.1.1",
        "0.10.2",
        "0.11.0",
        "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",
        "0.9.0",
        "0.9.0.1",
        "0.9.1",
        "0.9.2"
      ]
    }
  ],
  "aliases": [
    "CVE-2025-62372",
    "GHSA-pmqf-x6x8-p7qw"
  ],
  "details": "### Summary\n\nUsers can crash the vLLM engine serving multimodal models by passing multimodal embedding inputs with correct `ndim` but incorrect `shape` (e.g. hidden dimension is wrong), regardless of whether the model is intended to support such inputs (as defined in the Supported Models page).\n\nThe issue has existed ever since we added support for image embedding inputs, i.e. #6613 (released in v0.5.5)\n\n### Details\n\nUsing image embeddings as an example:\n\n- For models that support image embedding inputs, the engine crashes when scattering the embeddings to `inputs_embeds` (mismatched shape)\n- For models that don\u0027t support image embedding inputs, the engine crashes when validating the inputs inside `get_input_embeddings` (validation fails).\n\nThis happens because we only validate `ndim` of the tensor, but not the full shape, in input processor (via `MultiModalDataParser`).\n\n### Impact\n\n- Denial of service by crashing the engine\n\n### Mitigation\n\n- Use API key to limit access to trusted users.\n- Set `--limit-mm-per-prompt` to 0 for all non-text modalities to ban multimodal inputs, which includes multimodal embedding inputs. However, the model would then only accept text, defeating the purpose of using a multi-modal model.\n\n### Resolution\n\n- https://github.com/vllm-project/vllm/pull/27204",
  "id": "PYSEC-2026-2019",
  "modified": "2026-07-07T17:25:47.749093Z",
  "published": "2026-07-07T16:03:10.697627Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-pmqf-x6x8-p7qw"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2025-62372"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/pull/27204"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/pull/6613"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/commit/58fab50d82838d5014f4a14d991fdb9352c9c84b"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/vllm-project/vllm"
    },
    {
      "type": "PACKAGE",
      "url": "https://pypi.org/project/vllm"
    },
    {
      "type": "ADVISORY",
      "url": "https://github.com/advisories/GHSA-pmqf-x6x8-p7qw"
    }
  ],
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
      "type": "CVSS_V3"
    },
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:H",
      "type": "CVSS_V4"
    }
  ],
  "summary": "vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs"
}

CVE-2025-62372 (GCVE-0-2025-62372)

Vulnerability from cvelistv5 – Published: 2025-11-21 01:22 – Updated: 2025-11-24 18:11

Title

vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs

Summary

vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, users can crash the vLLM engine serving multimodal models by passing multimodal embedding inputs with correct ndim but incorrect shape (e.g. hidden dimension is wrong), regardless of whether the model is intended to support such inputs (as defined in the Supported Models page). This issue has been patched in version 0.11.1.

Severity

8.3 (High)


                        
                          CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:H

SSVC

Exploitation: none Automatable: no Technical Impact: partial

CISA Coordinator · CISA-ADP (v2.0.3)

Decision recorded 2025-11-24 17:07 UTC

CWE

CWE-129 - Improper Validation of Array Index

Assigner

GitHub_M CNA under the mitre root

CNA scorecard C 72/100 over 7886 records in the last 180 days details

References

4 references

URL	Tags
https://github.com/vllm-project/vllm/security/adv…	x_refsource_CONFIRM
https://github.com/vllm-project/vllm/pull/27204	x_refsource_MISC
https://github.com/vllm-project/vllm/pull/6613	x_refsource_MISC
https://github.com/vllm-project/vllm/commit/58fab…	x_refsource_MISC

Impacted products

1 product

Vendor	Product	Version
vllm-project	vllm	Affected: >= 0.5.5, < 0.11.1

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2025-62372",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2025-11-24T17:07:55.989854Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2025-11-24T18:11:59.207Z",
          "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= 0.5.5, \u003c 0.11.1"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, users can crash the vLLM engine serving multimodal models by passing multimodal embedding inputs with correct ndim but incorrect shape (e.g. hidden dimension is wrong), regardless of whether the model is intended to support such inputs (as defined in the Supported Models page). This issue has been patched in version 0.11.1."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "attackComplexity": "LOW",
            "attackRequirements": "NONE",
            "attackVector": "NETWORK",
            "baseScore": 8.3,
            "baseSeverity": "HIGH",
            "privilegesRequired": "LOW",
            "subAvailabilityImpact": "HIGH",
            "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:H",
            "version": "4.0",
            "vulnAvailabilityImpact": "HIGH",
            "vulnConfidentialityImpact": "NONE",
            "vulnIntegrityImpact": "NONE"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-129",
              "description": "CWE-129: Improper Validation of Array Index",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2025-11-21T01:22:37.121Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-pmqf-x6x8-p7qw",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-pmqf-x6x8-p7qw"
        },
        {
          "name": "https://github.com/vllm-project/vllm/pull/27204",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/pull/27204"
        },
        {
          "name": "https://github.com/vllm-project/vllm/pull/6613",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/pull/6613"
        },
        {
          "name": "https://github.com/vllm-project/vllm/commit/58fab50d82838d5014f4a14d991fdb9352c9c84b",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/commit/58fab50d82838d5014f4a14d991fdb9352c9c84b"
        }
      ],
      "source": {
        "advisory": "GHSA-pmqf-x6x8-p7qw",
        "discovery": "UNKNOWN"
      },
      "title": "vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2025-62372",
    "datePublished": "2025-11-21T01:22:37.121Z",
    "dateReserved": "2025-10-10T14:22:48.204Z",
    "dateUpdated": "2025-11-24T18:11:59.207Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2"
}

GHSA-PMQF-X6X8-P7QW

Vulnerability from github – Published: 2025-11-20 21:23 – Updated: 2026-07-17 16:15

Summary

vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs

Details

Summary

The issue has existed ever since we added support for image embedding inputs, i.e. #6613 (released in v0.5.5)

Details

Using image embeddings as an example:

For models that support image embedding inputs, the engine crashes when scattering the embeddings to inputs_embeds (mismatched shape)
For models that don't support image embedding inputs, the engine crashes when validating the inputs inside get_input_embeddings (validation fails).

This happens because we only validate ndim of the tensor, but not the full shape, in input processor (via MultiModalDataParser).

Impact

Denial of service by crashing the engine

Mitigation

Use API key to limit access to trusted users.
Set --limit-mm-per-prompt to 0 for all non-text modalities to ban multimodal inputs, which includes multimodal embedding inputs. However, the model would then only accept text, defeating the purpose of using a multi-modal model.

Resolution

https://github.com/vllm-project/vllm/pull/27204

Severity

6.5 (Medium)


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

8.3 (High)


                  
                    CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:H

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "vllm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0.5.5"
            },
            {
              "fixed": "0.11.1"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2025-62372"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-129"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2025-11-20T21:23:29Z",
    "nvd_published_at": "2025-11-21T02:15:43Z",
    "severity": "HIGH"
  },
  "details": "### Summary\n\nUsers can crash the vLLM engine serving multimodal models by passing multimodal embedding inputs with correct `ndim` but incorrect `shape` (e.g. hidden dimension is wrong), regardless of whether the model is intended to support such inputs (as defined in the Supported Models page).\n\nThe issue has existed ever since we added support for image embedding inputs, i.e. #6613 (released in v0.5.5)\n\n### Details\n\nUsing image embeddings as an example:\n\n- For models that support image embedding inputs, the engine crashes when scattering the embeddings to `inputs_embeds` (mismatched shape)\n- For models that don\u0027t support image embedding inputs, the engine crashes when validating the inputs inside `get_input_embeddings` (validation fails).\n\nThis happens because we only validate `ndim` of the tensor, but not the full shape, in input processor (via `MultiModalDataParser`).\n\n### Impact\n\n- Denial of service by crashing the engine\n\n### Mitigation\n\n- Use API key to limit access to trusted users.\n- Set `--limit-mm-per-prompt` to 0 for all non-text modalities to ban multimodal inputs, which includes multimodal embedding inputs. However, the model would then only accept text, defeating the purpose of using a multi-modal model.\n\n### Resolution\n\n- https://github.com/vllm-project/vllm/pull/27204",
  "id": "GHSA-pmqf-x6x8-p7qw",
  "modified": "2026-07-17T16:15:51Z",
  "published": "2025-11-20T21:23:29Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-pmqf-x6x8-p7qw"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2025-62372"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/pull/27204"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/pull/6613"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/commit/58fab50d82838d5014f4a14d991fdb9352c9c84b"
    },
    {
      "type": "ADVISORY",
      "url": "https://github.com/advisories/GHSA-pmqf-x6x8-p7qw"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2019.yaml"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/vllm-project/vllm"
    },
    {
      "type": "WEB",
      "url": "https://pypi.org/project/vllm"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
      "type": "CVSS_V3"
    },
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:H",
      "type": "CVSS_V4"
    }
  ],
  "summary": "vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs"
}

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.

Vulnerability timeline

Sightings and recorded dates, grouped by day · UTC

Order JSON

How durations are calculated

Following the VTEM framework (Black Hat USA 2015), time to patch starts when the vendor or a coordinator was informed, total time to patch at discovery, and disclosure to patch at public disclosure; vendor response time runs from the report to its acknowledgement. Time to exploit and time unpatched start at the earliest discovery or report, falling back to public disclosure. Unpatched time ends at the first recorded patch, or the calculation time when no patch is recorded. Exploitation to patch shows the interval between those two events; a published proof of concept is a public exploit, not exploitation.

Each result shows its source dates. A negative interval means the end event came first; when date-only inputs leave the order open, the result says so. Date-only inputs are approximate. The earliest evidence wins: KEV report dates and sightings are labelled as such. Records describing another vulnerability are listed but never calculated from, and a PoC alone does not establish exploitation. Missing patch evidence does not prove that no patch exists. Filters below change the event list only.

Publication & reservation Sightings KEV catalogs Other timestamps

Loading timeline…

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-2026-2019

Summary

Details

Impact

Mitigation

Resolution

CVE-2025-62372 (GCVE-0-2025-62372)

GHSA-PMQF-X6X8-P7QW

Summary

Details

Impact

Mitigation

Resolution

Tags

Sightings

Nomenclature

Vulnerability timeline

Related by attack behaviour