We use these services and cookies to improve your user experience. You may opt out if you wish, however, this may limit some features on this site.
Please see our statement on Data Privacy.
vLLM is an inference and serving engine for large language models (LLMs). In versions 0.8.0 up to but excluding 0.9.0, hitting the /v1/completions API with a invalid json_schema as a Guided Param kills the vllm server. This vulnerability is similar GHSA-9hcf-v7m4-6m2j/CVE-2025-48943, but for regex instead of a JSON schema. Version 0.9.0 fixes the issue.
Reserved 2025-05-28 | Published 2025-05-30 | Updated 2025-05-30 | Assigner GitHub_Mgithub.com/...t/vllm/security/advisories/GHSA-6qc9-v4r8-22xg
github.com/vllm-project/vllm/issues/17248
github.com/vllm-project/vllm/pull/17623
github.com/...ommit/08bf7840780980c7568c573c70a6a8db94fd45ff
Support options