Vulnerability Description
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.
CVSS Score
MEDIUM
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Vllm | Vllm | >= 0.8.0, < 0.9.0 |
Related Weaknesses (CWE)
References
- https://github.com/vllm-project/vllm/commit/08bf7840780980c7568c573c70a6a8db94fdPatch
- https://github.com/vllm-project/vllm/issues/17248Issue Tracking
- https://github.com/vllm-project/vllm/pull/17623Issue TrackingPatch
- https://github.com/vllm-project/vllm/security/advisories/GHSA-6qc9-v4r8-22xgExploitVendor Advisory
FAQ
What is CVE-2025-48942?
CVE-2025-48942 is a vulnerability with a CVSS score of 6.5 (MEDIUM). 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 kil...
How severe is CVE-2025-48942?
CVE-2025-48942 has been rated MEDIUM with a CVSS base score of 6.5/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2025-48942?
Check the references section above for vendor advisories and patch information. Affected products include: Vllm Vllm.