216.73.216.6

CVE-2026-22778

· Published 02/02/2026 23:16 · Modified 03/02/2026 16:44

Labels: CVE-2026-22778 2026-02-02CVE-2026-22778CWE-532[email protected]

Essential information

Published
02/02/2026 23:16
Modified
03/02/2026 16:44
Author
Creator
CVSS
9.8 CRITICAL (v3.1)
CISA KEV
No
CWE
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

CVSS metrics

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.

NVD status

Status
Undergoing Analysis — CVE has been recently published to the CVE List and has been received by the NVD.
Source
[email protected]
NVD
View on NVD

Affected products (CPE)

ProductCPE
llm / vllm cpe:2.3:a:llm:vllm:0.8.3-0.14.0:*:*:*:*:*:*:*
python / pillow cpe:2.3:a:python:pillow:*:*:*:*:*:*:*:*
opencv / opencv cpe:2.3:a:opencv:opencv:*:*:*:*:*:*:*
ffmpeg / ffmpeg cpe:2.3:a:ffmpeg:ffmpeg:*:*:*:*:*:*:*

References