CVE-2025-32381
MEDIUMmlc-ai xgrammar < 0.1.18 - Denial of Service via Unbounded Grammar Cache
Title source: llmDescription
XGrammar is an open-source library for efficient, flexible, and portable structured generation. Prior to 0.1.18, Xgrammar includes a cache for compiled grammars to increase performance with repeated use of the same grammar. This cache is held in memory. Since the cache is unbounded, a system making use of xgrammar can be abused to fill up a host's memory and case a denial of service. For example, sending many small requests to an LLM inference server with unique JSON schemas would eventually cause this denial of service to occur. This vulnerability is fixed in 0.1.18.
References (3)
Core 3
Core References
Vendor Advisory x_refsource_confirm
https://github.com/mlc-ai/xgrammar/security/advisories/GHSA-389x-67px-mjg3
Issue Tracking, Patch x_refsource_misc
https://github.com/mlc-ai/xgrammar/pull/243
Issue Tracking, Patch x_refsource_misc
https://github.com/vllm-project/vllm/pull/16283
Scores
CVSS v3
6.5
EPSS
0.0035
EPSS Percentile
57.8%
Attack Vector
NETWORK
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CISA SSVC
Vulnrichment
Exploitation
none
Automatable
no
Technical Impact
partial
Details
CWE
CWE-770
Status
published
Products (2)
mlc-ai/xgrammar
< 0.1.18
pypi/xgrammar
0 - 0.1.18PyPI
Published
Apr 09, 2025
Tracked Since
Feb 18, 2026