—

PYSEC-2025-55

상세

vLLM is an inference and serving engine for large language models (LLMs). Version 0.8.0 up to but excluding 0.9.0 have a Denial of Service (ReDoS) that causes the vLLM server to crash if an invalid regex was provided while using structured output. This vulnerability is similar to GHSA-6qc9-v4r8-22xg/CVE-2025-48942, but for regex instead of a JSON schema. Version 0.9.0 fixes the issue.

이 버전이 영향받나요?

사용 중인 패키지 버전을 입력하면 즉시 평가합니다.

영향 패키지

PyPI / vllm

최초 영향 버전: 0 수정 버전: 08bf7840780980c7568c573c70a6a8db94fd45ff

수정 pip install --upgrade 'vllm>=08bf7840780980c7568c573c70a6a8db94fd45ff'

참고

https://github.com/vllm-project/vllm/security/advisories/GHSA-9hcf-v7m4-6m2j [ADVISORY]
https://github.com/vllm-project/vllm/commit/08bf7840780980c7568c573c70a6a8db94fd45ff [FIX]
https://github.com/vllm-project/vllm/pull/17623 [REPORT]
https://github.com/vllm-project/vllm/issues/17313 [REPORT]