CVE-2026-55646

Gravedad CVSS v3.1:

MEDIA

Tipo:

CWE-400 Consumo de recursos no controlado (Agotamiento de recursos)

Fecha de publicación:

06/07/2026

Última modificación:

07/07/2026

Descripción

*** Pendiente de traducción *** vLLM is an inference and serving engine for large language models. From 0.22.0 to 0.23.0, the /v1/audio/transcriptions and /v1/audio/translations routes call request.file.read() to fully materialize an uploaded audio file into memory before vLLM checks the documented VLLM_MAX_AUDIO_CLIP_FILESIZE_MB compressed upload size limit (default 25 MB) later in the speech-to-text preprocessing step, so an API caller who can reach those routes can submit an oversized multipart upload and cause vLLM to allocate memory proportional to the uploaded file size before the request is rejected as too large, creating memory pressure or terminating the process depending on deployment resource limits. This issue is fixed in version 0.24.0.

Impacto

Vector 3.x

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H CVSS v3.1 Severidad y Métricas:

Puntuación base: 6.50 MEDIA
Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

Vector de acceso (AV): A través de red
Complejidad de acceso (AC): Bajo
Privilegios Requeridos (PR): Bajo
Interacción del usuario (UI): Ninguno
Alcance (S): Sin modificar
Impacto a la confidencialidad (C): Ninguno
Impacto a la integridad (I): Ninguno
Impacto a la disponibilidad (A): Alto