CVE-2026-22778

🚨 CRITICAL

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 th...

Published
Feb 02, 2026
Last Modified
Feb 03, 2026
Views
28
Bookmarks
0

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.

CVSS Scores

CVSS 3.1 9.8
9.8
CRITICAL
CVSS 2.0 9.8

Additional Information

Source
security-advisories@github.com
State
Undergoing analysis

Share CVE-2026-22778

Share on Social Media

Copy Link

Embed Code

Request Expert Analysis

Request a professional security analysis for CVE-2026-22778 from our verified experts.

Credits System

Use your credits to get expert analysis from verified security professionals. Purchase more credits anytime!

Add 3 credits for accelerated delivery

Base Cost: 8 credits
Priority Upgrade: + credits
SLA Acceleration: +3 credits
Total Cost:
Your Balance:

Insufficient Credits

You need more credits to submit this request.

Buy Credits

Report Analysis