Логотип exploitDog
Консоль
Логотип exploitDog

exploitDog

redhat логотип

CVE-2026-41523

Опубликовано: 22 июн. 2026
Источник: redhat
CVSS3: 7.5
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.

A flaw was found in vLLM, an inference and serving engine for large language models (LLMs). An unauthenticated attacker can exploit an assert-based security check during activation function loading. By publishing a malicious HuggingFace model, an attacker can achieve arbitrary code execution on the server when vLLM runs in Python optimized mode.

Отчет

Red Hat rates this issue as having Important impact for Red Hat AI Inference Server and Red Hat OpenShift AI vLLM serving images, and Moderate impact for Red Hat Enterprise Linux AI bootc images that bundle vLLM. Exploitation requires loading an untrusted HuggingFace cross-encoder model while the vLLM process runs with Python optimized mode (python -O or PYTHONOPTIMIZE=1). Red Hat AI Inference Server 3.2/3.3 images and other components without the vulnerable pooler activation loader (vLLM < 0.14.0) are not affected.

Меры по смягчению последствий

Avoid running vLLM with python -O or PYTHONOPTIMIZE=1 until updated packages are available. Only load models from trusted sources. Restrict who can deploy or update models on inference endpoints. Apply network access controls and authentication in front of vLLM APIs.

Затронутые пакеты

ПлатформаПакетСостояниеРекомендацияРелиз
Red Hat AI Inference Serverrhaiis/vllm-cpu-rhel9Not affected
Red Hat AI Inference Serverrhaiis/vllm-neuron-rhel9Not affected
Red Hat AI Inference Serverrhaiis/vllm-spyre-rhel9Not affected
Red Hat AI Inference Serverrhaiis/vllm-tpu-rhel9Not affected
Red Hat AI Inference Serverrhaii/vllm-cpu-rhel9Affected
Red Hat AI Inference Serverrhaii/vllm-gaudi-rhel9Affected
Red Hat AI Inference Serverrhaii/vllm-neuron-rhel9Not affected
Red Hat AI Inference Serverrhaii/vllm-spyre-rhel9Affected
Red Hat AI Inference Serverrhaii/vllm-tpu-rhel9Not affected
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-aws-cuda-rhel9Affected

Показывать по

Дополнительная информация

Статус:

Important
Дефект:
CWE-617
https://bugzilla.redhat.com/show_bug.cgi?id=2491582vllm: vLLM: Arbitrary code execution via malicious HuggingFace model

EPSS

Процентиль: 51%
0.00746
Низкий

7.5 High

CVSS3

Связанные уязвимости

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
debian
около 2 месяцев назад

vLLM is an inference and serving engine for large language models (LLM ...

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: 51%
0.00746
Низкий

7.5 High

CVSS3