- CVSS
- MEDIUM · 6.5v3.1CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
- Published
- 2025-11-21
- Weakness
- CWE-770
- Source
- nvd.nist.gov/vuln/detail/CVE-2025-62426
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.
References
- 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
- https://github.com/vllm-project/vllm/commit/3ada34f9cb4d1af763fdfa3b481862a93eb6bd2b
- https://github.com/vllm-project/vllm/pull/27205
- https://github.com/vllm-project/vllm/security/advisories/GHSA-69j4-grxj-j64p
How GTK Cyber trains on this
AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2025-62426 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.