Skip to content
NewA calmer, faster ZeroHour

CVE-2026-22778

CVSS 3.1
9.8 critical
EPSS
4%p89
Published
·
Modified
Analyze CVE-2026-22778 with Vani AIImpact, affected versions, exploitation status, mitigations and detection

Description · NVD

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.

Vendors
vllm
Products
vllm
Weakness
CWE-532, CWE-209
Vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

In the news

1 story