Home

Description

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.

PUBLISHED Reserved 2025-05-28 | Published 2025-05-30 | Updated 2025-05-30 | Assigner GitHub_M




MEDIUM: 6.5CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

Problem types

CWE-248: Uncaught Exception

Product status

>= 0.8.0, < 0.9.0
affected

References

github.com/...t/vllm/security/advisories/GHSA-9hcf-v7m4-6m2j

github.com/vllm-project/vllm/issues/17313

github.com/vllm-project/vllm/pull/17623

github.com/...ommit/08bf7840780980c7568c573c70a6a8db94fd45ff

cve.org (CVE-2025-48943)

nvd.nist.gov (CVE-2025-48943)

Download JSON