CVE-2025-48944

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.
References
Configurations

Configuration 1 (hide)

cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*

History

01 Jul 2025, 20:42

Type Values Removed Values Added
First Time Vllm
Vllm vllm
CPE cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
Summary
  • (es) vLLM es un motor de inferencia y servicio para modelos de lenguaje grandes (LLM). Desde la versión 0.8.0 hasta la 0.9.0 (excluyendo esta última), el backend de vLLM utilizado con el endpoint de OpenAPI /v1/chat/completions no valida entradas inesperadas o incorrectas en los campos "patrón" y "tipo" al invocar la funcionalidad de herramientas. Estas entradas no se validan antes de compilarse o analizarse, lo que provoca un bloqueo del trabajador de inferencia con una sola solicitud. El trabajador permanece inactivo hasta que se reinicia. La versión 0.9.0 corrige este problema.
References () https://github.com/vllm-project/vllm/pull/17623 - () https://github.com/vllm-project/vllm/pull/17623 - Issue Tracking, Vendor Advisory
References () https://github.com/vllm-project/vllm/security/advisories/GHSA-vrq3-r879-7m65 - () https://github.com/vllm-project/vllm/security/advisories/GHSA-vrq3-r879-7m65 - Exploit, Vendor Advisory

30 May 2025, 19:15

Type Values Removed Values Added
New CVE

Information

Published : 2025-05-30 19:15

Updated : 2025-07-01 20:42


NVD link : CVE-2025-48944

Mitre link : CVE-2025-48944

CVE.ORG link : CVE-2025-48944


JSON object : View

Products Affected

vllm

  • vllm
CWE
CWE-20

Improper Input Validation