Resource exhaustion in Mlc-Ai Xgrammar
CVE-2025-32381
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.
EPSS exploit prediction
EPSS: 0.005 (40.3th percentile), scored .
Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 40th percentile — 40.3% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.
EPSS over last 30 days · oldest: 0.005 · newest: 0.005 · change: +0.000
Affected products
- Mlc-Ai Xgrammar — versions < 0.1.18
Weakness classification (CWE)
References
- github.com/mlc-ai/xgrammar/security/advisories/GHSA-389x-67px-mjg3 (Vendor Advisory)
- github.com/mlc-ai/xgrammar/pull/243 (Patch, Issue Tracking)
- github.com/vllm-project/vllm/pull/16283 (Patch, Issue Tracking)
Frequently asked questions
- What is CVE-2025-32381?
- CVE-2025-32381 is a medium-severity vulnerability in Mlc-Ai Xgrammar, classified under Allocation of Resources Without Limits or Throttling. CVSS score: 6.5/10. Published 2025-04-09.
- How severe is CVE-2025-32381?
- Medium severity. CVSS v3 base score is 6.5 out of 10.