Логотип exploitDog
Консоль
Логотип exploitDog

exploitDog

redhat логотип

CVE-2025-59425

Опубликовано: 07 окт. 2025
Источник: redhat
CVSS3: 7.5

Описание

vLLM is an inference and serving engine for large language models (LLMs). Before version 0.11.0rc2, the API key support in vLLM performs validation using a method that was vulnerable to a timing attack. API key validation uses a string comparison that takes longer the more characters the provided API key gets correct. Data analysis across many attempts could allow an attacker to determine when it finds the next correct character in the key sequence. Deployments relying on vLLM's built-in API key validation are vulnerable to authentication bypass using this technique. Version 0.11.0rc2 fixes the issue.

A flaw was found in vLLM’s API token authentication logic, where token comparisons were not performed in constant time. This weakness could allow an attacker to exploit timing differences to guess valid tokens and bypass authentication.

Отчет

The RedHat security team has rated the severity of this issue as Important. The vulnerability is remotely exploitable without authentication or user interaction and can result in authentication bypass. The root cause was the use of a non-constant-time string comparison, which leaked timing information. Successful exploitation could lead to unauthorized access to APIs and sensitive resources.

Меры по смягчению последствий

Mitigation for this issue is either not available or the currently available options don't meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base or stability.

Затронутые пакеты

ПлатформаПакетСостояниеРекомендацияРелиз
Red Hat AI Inference Serverrhaiis/vllm-spyre-rhel9Will not fix
Red Hat AI Inference Serverrhaiis/vllm-tpu-rhel9Will not fix
Red Hat Enterprise Linux AI (RHEL AI)rhelai1/bootc-amd-rhel9Will not fix
Red Hat Enterprise Linux AI (RHEL AI)rhelai1/bootc-aws-nvidia-rhel9Will not fix
Red Hat Enterprise Linux AI (RHEL AI)rhelai1/bootc-azure-amd-rhel9Will not fix
Red Hat Enterprise Linux AI (RHEL AI)rhelai1/bootc-azure-nvidia-rhel9Will not fix
Red Hat Enterprise Linux AI (RHEL AI)rhelai1/bootc-gcp-nvidia-rhel9Will not fix
Red Hat Enterprise Linux AI (RHEL AI)rhelai1/bootc-intel-rhel9Will not fix
Red Hat Enterprise Linux AI (RHEL AI)rhelai1/bootc-nvidia-rhel9Will not fix
Red Hat Enterprise Linux AI (RHEL AI)rhelai1/instructlab-amd-rhel9Will not fix

Показывать по

Дополнительная информация

Статус:

Important
Дефект:
CWE-208
https://bugzilla.redhat.com/show_bug.cgi?id=2397234vllm: Timing Attack in vLLM API Token Verification Leading to Authentication Bypass

7.5 High

CVSS3

Связанные уязвимости

CVSS3: 7.5
nvd
6 месяцев назад

vLLM is an inference and serving engine for large language models (LLMs). Before version 0.11.0rc2, the API key support in vLLM performs validation using a method that was vulnerable to a timing attack. API key validation uses a string comparison that takes longer the more characters the provided API key gets correct. Data analysis across many attempts could allow an attacker to determine when it finds the next correct character in the key sequence. Deployments relying on vLLM's built-in API key validation are vulnerable to authentication bypass using this technique. Version 0.11.0rc2 fixes the issue.

CVSS3: 7.5
debian
6 месяцев назад

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

CVSS3: 7.5
github
6 месяцев назад

vLLM is vulnerable to timing attack at bearer auth

CVSS3: 7.5
fstec
6 месяцев назад

Уязвимость класса AuthenticationMiddleware библиотеки для работы с большими языковыми моделями (LLM) vLLM, позволяющая нарушителю обойти ограничения безопасности и раскрыть защищаемую информацию

7.5 High

CVSS3