← Voltar para CVEs

CVE-2026-22778

CRITICAL

9.8

Descricao

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.

Detalhes CVE

Pontuacao CVSS v3.19.8

SeveridadeCRITICAL

Vetor CVSSCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Vetor de ataqueNETWORK

ComplexidadeLOW

Privilegios necessariosNONE

Interacao do usuarioNONE

Publicado2/2/2026

Ultima modificacao2/23/2026

Fontenvd

Avistamentos honeypot0

Produtos afetados

vllm:vllm

Fraquezas (CWE)

CWE-532

Referencias

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)

Correlacoes IOC

Sem correlacoes registradas

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