CNNVD-202511-2540 Information

CNNVD ID

CNNVD-202511-2540

CVE-2025-62426

  • CNNVD Published: 2025-11-21

Description (Chinese)

vLLM是vLLM开源的一个适用于 LLM 的高吞吐量和内存高效推理和服务引擎。 vLLM 0.5.5版本至0.11.1之前版本存在安全漏洞,该漏洞源于chat_template_kwargs参数验证不足,可能导致API服务器处理阻塞。

Description (English)

vLLM is a high-volume throughput and memory efficient reasoning and service engine for VLLM open source. There is a security gap between vLM version 0.5.5 and pre-0.11.1, which stems from the lack of verification of the parameters of chat template kwargs, which may lead to obstruction of API processing.

Hazard Level

High

Vulnerability Type

其他

Affected Vendor

vLLM

Published

2025-11-21

Last Modified

2026-02-24

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

Patch

https://github.com/vllm-project/vllm/releases

Share on: