9.8
/ 10
CRITICAL
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Description
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.
Basic Information
ID
CVE-2026-22778
Source
GitHub_M
Published
Feb 2, 2026 at 21:09
Affected Product
Vendor
vllm-project
Product
vllm
Version
>= 0.8.3, < 0.14.1
Affected Versions
vllm-project vllm >= 0.8.3, < 0.14.1