Логотип exploitDog
Консоль
Логотип exploitDog

exploitDog

github логотип

GHSA-wr9h-g72x-mwhm

Опубликовано: 07 окт. 2025
Источник: github
Github: Прошло ревью
CVSS3: 7.5

Описание

vLLM is vulnerable to timing attack at bearer auth

Summary

The API key support in vLLM performed validation using a method that was vulnerable to a timing attack. This could potentially allow an attacker to discover a valid API key using an approach more efficient than brute force.

Details

https://github.com/vllm-project/vllm/blob/4b946d693e0af15740e9ca9c0e059d5f333b1083/vllm/entrypoints/openai/api_server.py#L1270-L1274

API key validation used a string comparison that will take longer the more characters the provided API key gets correct. Data analysis across many attempts can allow an attacker to determine when it finds the next correct character in the key sequence.

Impact

Deployments relying on vLLM's built-in API key validation are vulnerable to authentication bypass using this technique.

Пакеты

Наименование

vllm

pip
Затронутые версииВерсия исправления

< 0.11.0

0.11.0

EPSS

Процентиль: 63%
0.00455
Низкий

7.5 High

CVSS3

Дефекты

CWE-385

Связанные уязвимости

CVSS3: 7.5
nvd
4 месяца 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
4 месяца назад

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

CVSS3: 7.5
fstec
4 месяца назад

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

EPSS

Процентиль: 63%
0.00455
Низкий

7.5 High

CVSS3

Дефекты

CWE-385