← Zuruck zu CVEs

CVE-2026-22778

CRITICAL

9.8

Beschreibung

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 Bewertung9.8

SchweregradCRITICAL

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

AngriffsvektorNETWORK

KomplexitatLOW

Erforderliche PrivilegienNONE

BenutzerinteraktionNONE

Veroffentlicht2/2/2026

Zuletzt geandert2/23/2026

Quellenvd

Honeypot-Sichtungen0

Betroffene Produkte

vllm:vllm

Schwachen (CWE)

CWE-532

Referenzen

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 Korrelationen

Keine Korrelationen erfasst

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