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.
| Package (Ecosystem) | Introduced | Fixed | Limit |
|---|---|---|---|
| vllm(PyPI) | 0.8.0 | 0.9.0 | N/A |
CVSS Metrics
