CVE-2026-34755
Gravedad CVSS v3.1:
MEDIA
Tipo:
No Disponible / Otro tipo
Fecha de publicación:
06/04/2026
Última modificación:
06/04/2026
Descripción
*** Pendiente de traducción *** vLLM is an inference and serving engine for large language models (LLMs). From 0.7.0 to before 0.19.0, the VideoMediaIO.load_base64() method at vllm/multimodal/media/video.py splits video/jpeg data URLs by comma to extract individual JPEG frames, but does not enforce a frame count limit. The num_frames parameter (default: 32), which is enforced by the load_bytes() code path, is completely bypassed in the video/jpeg base64 path. An attacker can send a single API request containing thousands of comma-separated base64-encoded JPEG frames, causing the server to decode all frames into memory and crash with OOM. This vulnerability is fixed in 0.19.0.
Impacto
Puntuación base 3.x
6.50
Gravedad 3.x
MEDIA