Resource exhaustion in Mlc-Ai Xgrammar
CVE-2025-58446
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.
Published · last modified .
CVSS v3 metric
CVSS v3 base score 7.5 (High). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H.
EPSS exploit prediction
EPSS: 0.005 (42.9th percentile), scored .
Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 43rd percentile — 42.9% 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 = 0.1.23, < 0.1.24, 0.1.23
Weakness classification (CWE)
Public proof-of-concept exploits
References
- github.com/mlc-ai/xgrammar/security/advisories/GHSA-9q5r-wfvf-rr7f (Exploit, Vendor Advisory)
- github.com/mlc-ai/xgrammar/commit/ced69c3ad2f8f61b516cc278a342e7c644383e27 (Patch)
Frequently asked questions
- What is CVE-2025-58446?
- CVE-2025-58446 is a high-severity vulnerability in Mlc-Ai Xgrammar, classified under Allocation of Resources Without Limits or Throttling. CVSS score: 7.5/10. Published 2025-09-06.
- How severe is CVE-2025-58446?
- High severity. CVSS v3 base score is 7.5 out of 10.
- Is CVE-2025-58446 known to be exploited?
- 2 public proof-of-concept repositories are indexed. Not currently listed in the CISA KEV catalog.