CVE-2026-27893

HIGH

8.8

Descricao

vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.18.0, two model implementation files hardcode `trust_remote_code=True` when loading sub-components, bypassing the user's explicit `--trust-remote-code=False` security opt-out. This enables remote code execution via malicious model repositories even when the user has explicitly disabled remote code trust. Version 0.18.0 patches the issue.

Detalhes CVE

Pontuacao CVSS v3.18.8

SeveridadeHIGH

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

Vetor de ataqueNETWORK

ComplexidadeLOW

Privilegios necessariosNONE

Interacao do usuarioREQUIRED

Publicado3/27/2026

Ultima modificacao3/27/2026

Fontenvd

Avistamentos honeypot0

Fraquezas (CWE)

CWE-693

Referencias

https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72(security-advisories@github.com)

https://github.com/vllm-project/vllm/pull/36192(security-advisories@github.com)

https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59(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.