CVE-2025-48944

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 "type" 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.

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

Problem types

CWE-20: Improper Input Validation

Product status

>= 0.8.0, < 0.9.0
affected

References

github.com/...t/vllm/security/advisories/GHSA-vrq3-r879-7m65

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

cve.org (CVE-2025-48944)

nvd.nist.gov (CVE-2025-48944)

Download JSON