← Back to CVEs

CVE-2026-22778

CRITICAL

9.8

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.

CVE Details

CVSS v3.1 Score9.8

SeverityCRITICAL

CVSS VectorCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Attack VectorNETWORK

ComplexityLOW

Privileges RequiredNONE

User InteractionNONE

Published2/2/2026

Last Modified2/23/2026

Sourcenvd

Honeypot Sightings0

Affected Products

vllm:vllm

Weaknesses (CWE)

CWE-532

References

https://github.com/vllm-project/vllm/pull/31987(security-advisories@github.com)

https://github.com/vllm-project/vllm/pull/32319(security-advisories@github.com)

https://github.com/vllm-project/vllm/releases/tag/v0.14.1(security-advisories@github.com)

https://github.com/vllm-project/vllm/security/advisories/GHSA-4r2x-xpjr-7cvv(security-advisories@github.com)

IOC Correlations

No correlations recorded

This product uses data from the NVD API but is not endorsed or certified by the NVD.