CVE-2025-48944

MEDIUM

6.5

Descripcion

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.

Detalles CVE

Puntuacion CVSS v3.16.5

SeveridadMEDIUM

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

Vector de ataqueNETWORK

ComplejidadLOW

Privilegios requeridosLOW

Interaccion usuarioNONE

Publicado5/30/2025

Ultima modificacion7/1/2025

Fuentenvd

Avistamientos honeypot0

Productos afectados

vllm:vllm

Debilidades (CWE)

CWE-20

Referencias

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)

Correlaciones IOC

Sin correlaciones registradas

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