{"id":"CVE-2025-62426","state":"PUBLISHED","title":"vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`","description":"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.","publishedAt":"2025-11-21T01:21:29.546Z","updatedAt":"2025-11-24T18:12:23.183Z","severity":{"score":6.5,"label":"Medium","version":"3.1","vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","source":"GitHub_M"},"assigner":"GitHub_M","products":["vllm-project vllm"],"affected":[{"vendor":"vllm-project","product":"vllm","versions":[{"version":">= 0.5.5, < 0.11.1","status":"affected"}]}],"references":["https://github.com/vllm-project/vllm/security/advisories/GHSA-69j4-grxj-j64p","https://github.com/vllm-project/vllm/pull/27205","https://github.com/vllm-project/vllm/commit/3ada34f9cb4d1af763fdfa3b481862a93eb6bd2b","https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/chat_utils.py#L1602-L1610","https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/openai/serving_engine.py#L809-L814"],"weaknesses":["CWE-770"],"ingestedAt":"2026-10-29T20:09:48.677Z","source":{"repository":"CVEProject/cvelistV5","path":"cves/2025/62xxx/CVE-2025-62426.json","commit":"556c9d3a8cd17e218bb8e452ba7cd619a384ff47"},"raw":{"dataType":"CVE_RECORD","dataVersion":"5.2","cveMetadata":{"cveId":"CVE-2025-62426","state":"PUBLISHED","datePublished":"2025-11-21T01:21:29.546Z","dateUpdated":"2025-11-24T18:12:23.183Z","assignerShortName":"GitHub_M","assignerOrgId":"a0819718-46f1-4df5-94e2-005712e83aaa","dateReserved":"2025-10-13T16:26:12.180Z"},"containers":{"cna":{"title":"vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`","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."}],"affected":[{"vendor":"vllm-project","product":"vllm","versions":[{"version":">= 0.5.5, < 0.11.1","status":"affected"}]}],"references":[{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-69j4-grxj-j64p","name":"https://github.com/vllm-project/vllm/security/advisories/GHSA-69j4-grxj-j64p","tags":["x_refsource_CONFIRM"]},{"url":"https://github.com/vllm-project/vllm/pull/27205","name":"https://github.com/vllm-project/vllm/pull/27205","tags":["x_refsource_MISC"]},{"url":"https://github.com/vllm-project/vllm/commit/3ada34f9cb4d1af763fdfa3b481862a93eb6bd2b","name":"https://github.com/vllm-project/vllm/commit/3ada34f9cb4d1af763fdfa3b481862a93eb6bd2b","tags":["x_refsource_MISC"]},{"url":"https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/chat_utils.py#L1602-L1610","name":"https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/chat_utils.py#L1602-L1610","tags":["x_refsource_MISC"]},{"url":"https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/openai/serving_engine.py#L809-L814","name":"https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/openai/serving_engine.py#L809-L814","tags":["x_refsource_MISC"]}],"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-770","lang":"en","description":"CWE-770: Allocation of Resources Without Limits or Throttling","type":"CWE"}]}],"providerMetadata":{"shortName":"GitHub_M","orgId":"a0819718-46f1-4df5-94e2-005712e83aaa","dateUpdated":"2025-11-21T01:21:29.546Z"},"source":{"advisory":"GHSA-69j4-grxj-j64p","discovery":"UNKNOWN"}},"adp":[{"title":"CISA ADP Vulnrichment","metrics":[{"other":{"type":"ssvc","content":{"timestamp":"2025-11-24T17:12:00.809982Z","id":"CVE-2025-62426","options":[{"Exploitation":"none"},{"Automatable":"no"},{"Technical Impact":"partial"}],"role":"CISA Coordinator","version":"2.0.3"}}}],"providerMetadata":{"shortName":"CISA-ADP","orgId":"134c704f-9b21-4f2e-91b3-4a467353bcc0","dateUpdated":"2025-11-24T18:12:23.183Z"}}]}}}