CVE-2025-48944

vLLM Tool Schema allows DoS via Malformed pattern and type Fields

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.

Affected

vllm-project · vllm

CVSS v3.1 GITHUB

6.5 MEDIUMCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

EPSS

0.61% chance of exploitation in the next 30 days, 48th percentile

Published

2025-05-30

Proof-of-concept exploits (2)

• vllm-project/vllm/security/advisories/GHSA-vrq3-r879-7m65
• advisories/GHSA-vrq3-r879-7m65

Security advisories

• vllm-project/vllm/pull/17623

References

• CVE Record
• NVD entry