Логотип exploitDog
Консоль
Логотип exploitDog

exploitDog

debian логотип

CVE-2026-27893

Опубликовано: 27 мар. 2026
Источник: debian

Описание

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.

Пакеты

ПакетСтатусВерсия исправленияРелизТип
vllmitppackage

Связанные уязвимости

CVSS3: 8.8
redhat
5 дней назад

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.

CVSS3: 8.8
nvd
5 дней назад

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.

CVSS3: 8.8
github
4 дня назад

vLLM has Hardcoded Trust Override in Model Files Enables RCE Despite Explicit User Opt-Out