CVE-2026-22778
Gravedad CVSS v3.1:
CRÍTICA
Tipo:
CWE-532
Exposición de información a través de archivos de log
Fecha de publicación:
02/02/2026
Última modificación:
02/02/2026
Descripción
*** Pendiente de traducción *** vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM's multimodal endpoint, PIL throws an error. vLLM returns this error to the client, leaking a heap address. With this leak, we reduce ASLR from 4 billion guesses to ~8 guesses. This vulnerability can be chained a heap overflow with JPEG2000 decoder in OpenCV/FFmpeg to achieve remote code execution. This vulnerability is fixed in 0.14.1.
Impacto
Puntuación base 3.x
9.80
Gravedad 3.x
CRÍTICA



