Логотип exploitDog
Консоль
Логотип exploitDog

exploitDog

debian логотип

CVE-2026-41523

Опубликовано: 22 июн. 2026
Источник: debian
EPSS Низкий

Описание

vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, an assert-based security check in vLLM's activation function loading allows any unauthenticated attacker to achieve arbitrary code execution on the server by publishing a malicious HuggingFace model, when vLLM runs in Python optimized mode (python -O or PYTHONOPTIMIZE=1). This vulnerability is fixed in 0.22.0.

Пакеты

ПакетСтатусВерсия исправленияРелизТип
vllmitppackage

EPSS

Процентиль: 39%
0.00484
Низкий

Связанные уязвимости

CVSS3: 7.5
redhat
около 2 месяцев назад

vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, an assert-based security check in vLLM's activation function loading allows any unauthenticated attacker to achieve arbitrary code execution on the server by publishing a malicious HuggingFace model, when vLLM runs in Python optimized mode (python -O or PYTHONOPTIMIZE=1). This vulnerability is fixed in 0.22.0.

CVSS3: 7.5
nvd
около 2 месяцев назад

vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, an assert-based security check in vLLM's activation function loading allows any unauthenticated attacker to achieve arbitrary code execution on the server by publishing a malicious HuggingFace model, when vLLM runs in Python optimized mode (python -O or PYTHONOPTIMIZE=1). This vulnerability is fixed in 0.22.0.

CVSS3: 7.5
github
около 2 месяцев назад

vLLM: Security Check Bypass via assert Statement in Activation Function Loading Allows Arbitrary Code Execution

EPSS

Процентиль: 39%
0.00484
Низкий