CVE-2025-58446mediumCWE-770

CVE-2025-58446: medium-severity vulnerability in mlc-ai xgrammar

xgrammar vulnerable to denial of service by huge enum grammar

Published · Updated

Follow this CVE+ Monitor xgrammar+ Monitor xgrammar

E-mail alert when it lands in KEV, gets a public PoC or its score goes up.

13Vexday Risk Score

No sign of exploitation. No public exploitation artifact known so far.

ssvc Trackcvss 6.9epss 0.6%
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.
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N
Affected products
mlc-ai · xgrammar
Related CVEs — mlc-ai xgrammar

In the same product, most dangerous first.

CVE-2026-25048HIGHxgrammar: Multi-layer nesting causes DoSEPSS 1.3%CVE-2025-32381MEDIUMDenial of Service by abusing xgrammar unbounded cache in memoryEPSS 0.5%CVE-2025-57809HIGHXGrammar affected by Denial of Service by infinite recursion grammarsEPSS 0.5%