CVE-2025-48944 Information

Description

vLLM is an inference and serving engine for large language models (LLMs). In version 0.8.0 up to but excluding 0.9.0 the vLLM backend used with the /v1/chat/completions OpenAPI endpoint fails to validate unexpected or malformed input in the \pattern\ and ype\ fields when the tools functionality is invoked. These inputs are not validated before being compiled or parsed causing a crash of the inference worker with a single request. The worker will remain down until it is restarted. Version 0.9.0 fixes the issue.

Reference

https://github.com/vllm-project/vllm/pull/17623 https://github.com/vllm-project/vllm/security/advisories/GHSA-vrq3-r879-7m65