Vulnerability-Lookup

GHSA-PC5Q-2X89-W436

Vulnerability from github – Published: 2026-09-20 00:30 – Updated: 2026-09-20 00:30

Details

vLLM through 0.29.0 fails to properly validate bad_words token indices against the model's generation output width in SamplingParams.update_from_tokenizer(). Attackers can supply out-of-bounds token indices that corrupt logits memory of concurrent requests, causing different in-flight HTTP requests to return incorrect tokens.

Severity

3.1 (Low)


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

2.3 (Low)


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

Show details on source website

JSON

To clipboard

{
  "affected": [],
  "aliases": [
    "CVE-2026-93989"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-129"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2026-09-19T23:17:10Z",
    "severity": "LOW"
  },
  "details": "vLLM through 0.29.0 fails to properly validate bad_words token indices against the model\u0027s generation output width in SamplingParams.update_from_tokenizer(). Attackers can supply out-of-bounds token indices that corrupt logits memory of concurrent requests, causing different in-flight HTTP requests to return incorrect tokens.",
  "id": "GHSA-pc5q-2x89-w436",
  "modified": "2026-09-20T00:30:23Z",
  "published": "2026-09-20T00:30:23Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-93989"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/pull/48824"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/blob/98dff2a81d747d1dba01a47f939f48c3526d4206/vllm/sampling_params.py#L694-L753"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/blob/98dff2a81d747d1dba01a47f939f48c3526d4206/vllm/v1/worker/gpu/sample/bad_words.py"
    },
    {
      "type": "WEB",
      "url": "https://www.vulncheck.com/advisories/vllm-through-0.29.0-cross-request-logits-corruption-via-bad-words"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:N",
      "type": "CVSS_V3"
    },
    {
      "score": "CVSS:4.0/AV:N/AC:H/AT:P/PR:L/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
      "type": "CVSS_V4"
    }
  ]
}

CVE-2026-93989 (GCVE-0-2026-93989)

Vulnerability from cvelistv5 – Published: 2026-09-19 22:58 – Updated: 2026-09-22 16:00

Title

vLLM through 0.29.0 Cross-Request Logits Corruption via bad_words

Summary

Severity

2.3 (Low)


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

3.1 (Low)


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

SSVC

Exploitation: none Automatable: no Technical Impact: partial

CISA Coordinator · CISA-ADP (v2.0.3)

Decision recorded 2026-09-22 16:00 UTC

CWE

CWE-129 - Improper Validation of Array Index

Assigner

VulnCheck CNA under the mitre root

CNA scorecard B 84/100 over 6503 records in the last 180 days details

References

5 references

URL	Tags
https://github.com/vllm-project/vllm/pull/48824	issue-trackingpatch
https://github.com/vllm-project/vllm/blob/98dff2a…	technical-description
https://github.com/vllm-project/vllm/blob/98dff2a…	technical-description
https://github.com/vllm-project/vllm	product
https://www.vulncheck.com/advisories/vllm-through…	third-party-advisory

Impacted products

1 product

Vendor	Product	Version
vllm-project	vllm	Affected: 0 , ≤ 0.29.0 (semver) cpe:2.3:a:vllm:vllm::::::::

Date Public

2026-07-16 00:00

Credits

于明愷

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-93989",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-09-22T16:00:35.389361Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-09-22T16:00:44.177Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "defaultStatus": "unaffected",
          "packageURL": "pkg:pypi/vllm",
          "product": "vllm",
          "repo": "https://github.com/vllm-project/vllm",
          "vendor": "vllm-project",
          "versions": [
            {
              "lessThanOrEqual": "0.29.0",
              "status": "affected",
              "version": "0",
              "versionType": "semver"
            }
          ]
        }
      ],
      "cpeApplicability": [
        {
          "nodes": [
            {
              "cpeMatch": [
                {
                  "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
                  "versionEndIncluding": "0.29.0",
                  "vulnerable": true
                }
              ],
              "negate": false,
              "operator": "OR"
            }
          ]
        }
      ],
      "credits": [
        {
          "lang": "en",
          "type": "reporter",
          "value": "\u4e8e\u660e\u6137"
        }
      ],
      "datePublic": "2026-07-16T00:00:00.000Z",
      "descriptions": [
        {
          "lang": "en",
          "value": "vLLM through 0.29.0 fails to properly validate bad_words token indices against the model\u0027s generation output width in SamplingParams.update_from_tokenizer(). Attackers can supply out-of-bounds token indices that corrupt logits memory of concurrent requests, causing different in-flight HTTP requests to return incorrect tokens."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "attackComplexity": "HIGH",
            "attackRequirements": "PRESENT",
            "attackVector": "NETWORK",
            "baseScore": 2.3,
            "baseSeverity": "LOW",
            "privilegesRequired": "LOW",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "NONE",
            "vectorString": "CVSS:4.0/AV:N/AC:H/AT:P/PR:L/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N",
            "version": "4.0",
            "vulnAvailabilityImpact": "NONE",
            "vulnConfidentialityImpact": "NONE",
            "vulnIntegrityImpact": "LOW"
          },
          "format": "CVSS"
        },
        {
          "cvssV3_1": {
            "attackComplexity": "HIGH",
            "attackVector": "NETWORK",
            "availabilityImpact": "NONE",
            "baseScore": 3.1,
            "baseSeverity": "LOW",
            "confidentialityImpact": "NONE",
            "integrityImpact": "LOW",
            "privilegesRequired": "LOW",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:N",
            "version": "3.1"
          },
          "format": "CVSS"
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-129",
              "description": "Improper Validation of Array Index",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-09-19T22:58:10.572Z",
        "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "shortName": "VulnCheck"
      },
      "references": [
        {
          "name": "GitHub PR #48824",
          "tags": [
            "issue-tracking",
            "patch"
          ],
          "url": "https://github.com/vllm-project/vllm/pull/48824"
        },
        {
          "name": "_bad_words_kernel at v0.29.0",
          "tags": [
            "technical-description"
          ],
          "url": "https://github.com/vllm-project/vllm/blob/98dff2a81d747d1dba01a47f939f48c3526d4206/vllm/v1/worker/gpu/sample/bad_words.py"
        },
        {
          "name": "update_from_tokenizer at v0.29.0",
          "tags": [
            "technical-description"
          ],
          "url": "https://github.com/vllm-project/vllm/blob/98dff2a81d747d1dba01a47f939f48c3526d4206/vllm/sampling_params.py#L694-L753"
        },
        {
          "tags": [
            "product"
          ],
          "url": "https://github.com/vllm-project/vllm"
        },
        {
          "name": "VulnCheck Advisory: vLLM through 0.29.0 Cross-Request Logits Corruption via bad_words",
          "tags": [
            "third-party-advisory"
          ],
          "url": "https://www.vulncheck.com/advisories/vllm-through-0.29.0-cross-request-logits-corruption-via-bad-words"
        }
      ],
      "title": "vLLM through 0.29.0 Cross-Request Logits Corruption via bad_words",
      "x_generator": {
        "engine": "vulncheck-endgame"
      }
    }
  },
  "cveMetadata": {
    "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
    "assignerShortName": "VulnCheck",
    "cveId": "CVE-2026-93989",
    "datePublished": "2026-09-19T22:58:10.572Z",
    "dateReserved": "2026-09-19T10:55:49.093Z",
    "dateUpdated": "2026-09-22T16:00:44.177Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2"
}

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

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