Логотип exploitDog
Консоль
Логотип exploitDog

exploitDog

debian логотип

CVE-2025-48887

Опубликовано: 30 мая 2025
Источник: debian
EPSS Низкий

Описание

vLLM, an inference and serving engine for large language models (LLMs), has a Regular Expression Denial of Service (ReDoS) vulnerability in the file `vllm/entrypoints/openai/tool_parsers/pythonic_tool_parser.py` of versions 0.6.4 up to but excluding 0.9.0. The root cause is the use of a highly complex and nested regular expression for tool call detection, which can be exploited by an attacker to cause severe performance degradation or make the service unavailable. The pattern contains multiple nested quantifiers, optional groups, and inner repetitions which make it vulnerable to catastrophic backtracking. Version 0.9.0 contains a patch for the issue.

Пакеты

ПакетСтатусВерсия исправленияРелизТип
vllmitppackage

EPSS

Процентиль: 57%
0.00345
Низкий

Связанные уязвимости

CVSS3: 6.5
redhat
11 месяцев назад

vLLM, an inference and serving engine for large language models (LLMs), has a Regular Expression Denial of Service (ReDoS) vulnerability in the file `vllm/entrypoints/openai/tool_parsers/pythonic_tool_parser.py` of versions 0.6.4 up to but excluding 0.9.0. The root cause is the use of a highly complex and nested regular expression for tool call detection, which can be exploited by an attacker to cause severe performance degradation or make the service unavailable. The pattern contains multiple nested quantifiers, optional groups, and inner repetitions which make it vulnerable to catastrophic backtracking. Version 0.9.0 contains a patch for the issue.

CVSS3: 6.5
nvd
11 месяцев назад

vLLM, an inference and serving engine for large language models (LLMs), has a Regular Expression Denial of Service (ReDoS) vulnerability in the file `vllm/entrypoints/openai/tool_parsers/pythonic_tool_parser.py` of versions 0.6.4 up to but excluding 0.9.0. The root cause is the use of a highly complex and nested regular expression for tool call detection, which can be exploited by an attacker to cause severe performance degradation or make the service unavailable. The pattern contains multiple nested quantifiers, optional groups, and inner repetitions which make it vulnerable to catastrophic backtracking. Version 0.9.0 contains a patch for the issue.

CVSS3: 6.5
github
11 месяцев назад

vLLM has a Regular Expression Denial of Service (ReDoS, Exponential Complexity) Vulnerability in `pythonic_tool_parser.py`

CVSS3: 6.5
fstec
11 месяцев назад

Уязвимость сценария pythonic_tool_parser.py библиотеки для работы с большими языковыми моделями (LLM) vLLM, позволяющая нарушителю вызвать отказ в обслуживании

EPSS

Процентиль: 57%
0.00345
Низкий