« Volver al listado

CVE-2025-62426

Estado: AnalizadaMedia (6.5)—

vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, the /v1/chat/completions and /tokenize endpoints allow a chat_template_kwargs request parameter that is used in the code before it is properly validated against the chat template. With the right chat_template_kwargs parameters, it is possible to block processing of the API server for long periods of time, delaying all other requests. This issue has been patched in version 0.11.1.

CVSS

Probabilidad de explotación (EPSS)

EPSS (Exploit Prediction Scoring System, de FIRST) estima la probabilidad de que una vulnerabilidad sea explotada en 30 días. Complementa a CVSS (impacto) y a CISA KEV (explotación confirmada).

Tecnologías afectadas (1)

Vllm — Vllm

CWE

Referencias

JSON original (NVD)

Mostrar
{
  "id": "CVE-2025-62426",
  "cveTags": [],
  "metrics": {
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2025-62426",
          "role": "CISA Coordinator",
          "options": [
            {
              "exploitation": "none"
            },
            {
              "automatable": "no"
            },
            {
              "technicalImpact": "partial"
            }
          ],
          "version": "2.0.3",
          "timestamp": "2025-11-24T17:12:00.809982Z"
        }
      }
    ],
    "cvssMetricV31": [
      {
        "type": "Secondary",
        "source": "security-advisories@github.com",
        "cvssData": {
          "scope": "UNCHANGED",
          "version": "3.1",
          "baseScore": 6.5,
          "attackVector": "NETWORK",
          "baseSeverity": "MEDIUM",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
          "integrityImpact": "NONE",
          "userInteraction": "NONE",
          "attackComplexity": "LOW",
          "availabilityImpact": "HIGH",
          "privilegesRequired": "LOW",
          "confidentialityImpact": "NONE"
        },
        "impactScore": 3.6,
        "exploitabilityScore": 2.8
      }
    ]
  },
  "affected": [
    {
      "source": "security-advisories@github.com",
      "affectedData": [
        {
          "vendor": "vllm-project",
          "product": "vllm",
          "versions": [
            {
              "status": "affected",
              "version": ">= 0.5.5, < 0.11.1"
            }
          ]
        }
      ]
    }
  ],
  "published": "2025-11-21T02:15:43.570",
  "references": [
    {
      "url": "https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/chat_utils.py#L1602-L1610",
      "tags": [
        "Product"
      ],
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/openai/serving_engine.py#L809-L814",
      "tags": [
        "Product"
      ],
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/vllm-project/vllm/commit/3ada34f9cb4d1af763fdfa3b481862a93eb6bd2b",
      "tags": [
        "Patch"
      ],
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/vllm-project/vllm/pull/27205",
      "tags": [
        "Issue Tracking"
      ],
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-69j4-grxj-j64p",
      "tags": [
        "Vendor Advisory"
      ],
      "source": "security-advisories@github.com"
    }
  ],
  "vulnStatus": "Analyzed",
  "weaknesses": [
    {
      "type": "Secondary",
      "source": "security-advisories@github.com",
      "description": [
        {
          "lang": "en",
          "value": "CWE-770"
        }
      ]
    }
  ],
  "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, the /v1/chat/completions and /tokenize endpoints allow a chat_template_kwargs request parameter that is used in the code before it is properly validated against the chat template. With the right chat_template_kwargs parameters, it is possible to block processing of the API server for long periods of time, delaying all other requests. This issue has been patched in version 0.11.1."
    }
  ],
  "lastModified": "2026-06-17T09:51:53.037",
  "configurations": [
    {
      "nodes": [
        {
          "negate": false,
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
              "vulnerable": true,
              "matchCriteriaId": "BA1047E1-ED1E-4685-B699-8CE5B2058D87",
              "versionEndExcluding": "0.11.1",
              "versionStartIncluding": "0.5.5"
            },
            {
              "criteria": "cpe:2.3:a:vllm:vllm:0.11.1:rc0:*:*:*:*:*:*",
              "vulnerable": true,
              "matchCriteriaId": "FEE054E1-1F84-4ACC-894C-D7E3652EF1B1"
            },
            {
              "criteria": "cpe:2.3:a:vllm:vllm:0.11.1:rc1:*:*:*:*:*:*",
              "vulnerable": true,
              "matchCriteriaId": "B05850DF-38FE-439F-9F7A-AA96DA9038CC"
            }
          ],
          "operator": "OR"
        }
      ]
    }
  ],
  "sourceIdentifier": "security-advisories@github.com"
}