CVE-2025-62426
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.
Does this matter?
Lower severity and a low EPSS score (0.37%). Track it; it rarely justifies an emergency change on its own.
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.
- CVSS 3.1
- 6.5 MEDIUMCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
- EPSS
- 0.37% probability · 30th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-770
- Affected
- vllm/vllm
- Source
- security-advisories@github.com
References
- https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/chat_utils.py#L1602-L1610Product
- https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/openai/serving_engine.py#L809-L814Product
- https://github.com/vllm-project/vllm/commit/3ada34f9cb4d1af763fdfa3b481862a93eb6bd2bPatch
- https://github.com/vllm-project/vllm/pull/27205Issue Tracking
- https://github.com/vllm-project/vllm/security/advisories/GHSA-69j4-grxj-j64pVendor Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.