VULNERABILITY INTELLIGENCE

CVE-2026-22778

CVSS score9.8 CRITICAL
EPSS probability18.29%
CISA KEVNot currently listed
Published2026-02-02
Last modified2026-07-15
CVSS vectorCVSS: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.

Weakness classification

  • security-advisories@github.com: CWE-532
  • 0b0ca135-0b70-47e7-9f44-1890c2a1c46c: CWE-209

Primary references