Resource exhaustion in Mlc-Ai Xgrammar
CVE-2025-32381
- CVSS v3
- 6.5 Medium
- Public exploits
- None known
- EPSS
- 0.005 · 44.6th percentile
- Published
- 2025-04-09
What to do
- Fixed in
0.1.18- Affected
- 1 affected product
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.
Published · last modified .
CVSS v3 metric
CVSS v3 base score 6.5 (Medium). Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H.
- Attack Vector
- Network
AV:N - Attack Complexity
- Low
AC:L - Privileges Required
- Low
PR:L - User Interaction
- None
UI:N - Scope
- Unchanged
S:U - Confidentiality
- None
C:N - Integrity
- None
I:N - Availability
- High
A:H
EPSS exploit prediction
EPSS 0.005, 44.6th percentile (last changed ); unchanged over 30 days. About EPSS.
Affected products
- Mlc-Ai Xgrammar — versions < 0.1.18
Weakness classification (CWE)
References
- https://github.com/mlc-ai/xgrammar/security/advisories/GHSA-389x-67px-mjg3 (Vendor Advisory)
- https://github.com/mlc-ai/xgrammar/pull/243 (Patch, Issue Tracking)
- https://github.com/vllm-project/vllm/pull/16283 (Patch, Issue Tracking)