Описание
A vulnerability was found in vLLM's Qwen3 Coder tool parser. Since this parser uses Python's eval() function, it poses a risk of arbitrary code execution. This vulnerability appears during the parameter conversion process when the parser attempts to handle complex data types.
Отчет
This vulnerability was discovered and fixed in the upstream qwen3 component. It never affected any Red Hat products. The impact is Important as it could allow remote code execution. The precondition of an attacker needing valid login credentials, prevents it from being Critical.
Затронутые пакеты
| Платформа | Пакет | Состояние | Рекомендация | Релиз |
|---|---|---|---|---|
| Red Hat Enterprise Linux AI (RHEL AI) | rhelai1/deepseek-r1-0528-quantized-w4a16 | Not affected | ||
| Red Hat Enterprise Linux AI (RHEL AI) | rhelai1/gemma-3n-e4b-it | Not affected | ||
| Red Hat Enterprise Linux AI (RHEL AI) | rhelai1/kimi-k2-instruct-quantized-w4a16 | Not affected | ||
| Red Hat Enterprise Linux AI (RHEL AI) | rhelai1/modelcar-deepseek-r1-0528-quantized-w4a16 | Not affected | ||
| Red Hat Enterprise Linux AI (RHEL AI) | rhelai1/modelcar-gemma-3n-e4b-it | Not affected | ||
| Red Hat Enterprise Linux AI (RHEL AI) | rhelai1/modelcar-kimi-k2-instruct-quantized-w4a16 | Not affected | ||
| Red Hat Enterprise Linux AI (RHEL AI) | rhelai1/modelcar-qwen3-4b-quantized-w4a16 | Not affected | ||
| Red Hat Enterprise Linux AI (RHEL AI) | rhelai1/modelcar-smollm3-3b | Not affected | ||
| Red Hat Enterprise Linux AI (RHEL AI) | rhelai1/qwen3-4b-quantized-w4a16 | Not affected | ||
| Red Hat Enterprise Linux AI (RHEL AI) | rhelai1/smollm3-3b | Not affected |
Показывать по
10
Дополнительная информация
Статус:
Important
Дефект:
CWE-502
https://bugzilla.redhat.com/show_bug.cgi?id=2389395vllm: quen3: RCE in vllm tool call parser for qwen3coder
8.8 High
CVSS3
Связанные уязвимости
CVSS3: 8.8
github
5 дней назад
vLLM has remote code execution vulnerability in the tool call parser for Qwen3-Coder
8.8 High
CVSS3