Read the docs
TI-2025-23460 Aliases CVE-2025-32381GHSA-389x-67px-mjg3

Denial of Service by abusing xgrammar unbounded cache in memory

Priority LOW 29CWE-770Published · Updated

Key facts

Attack vector
Network
Privileges required
Low
User interaction
None
Attack complexity
Low
Impact type
Denial of service
Confidentiality · integrity · availability
None · None · High
Fix status
Partial Red Hat: 1 without a fix

Attack profile from CVSS 3.1 · CNA. Fix status from CNA, GitHub and Red Hat. Impact type from CWE-770.

Summary

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.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV
EPSS 0.00517 44th percentileScored 2026-11-07
Fix Partial xgrammar (mlc-ai): 0.1.18xgrammar (PyPI): 0.1.18Red Hat: 1 without a fix

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
None
Automatable
No
Technical impact
Partial

The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.

Affected products

VendorProductAffected versionsFixed inStatusSource
mlc-aixgrammarbefore 0.1.180.1.18Patch availableCNA
—xgrammar (PyPI)before 0.1.180.1.18Patch availableGHSA-389x-67px-mjg3
  • xgrammar Vendormlc-ai Affected before 0.1.18 Fixed in 0.1.18 Patch available CNA
  • xgrammar (PyPI) Vendor— Affected before 0.1.18 Fixed in 0.1.18 Patch available GHSA-389x-67px-mjg3

CPE configurations NVD · 1

CPEVersionsRoleVendor
cpe:2.3:a:mlc-ai:xgrammar:*:*:*:*:*:*:*:*before 0.1.18Vulnerablemlc-ai
  • cpe:2.3:a:mlc-ai:xgrammar:*:*:*:*:*:*:*:* Versions before 0.1.18 Vulnerable ·mlc-ai

Remediation

  • Fix · CNA xgrammar (mlc-ai) Fixed in 0.1.18
  • Fix · GHSA-389x-67px-mjg3 xgrammar (PyPI) Fixed in 0.1.18 Advisory →

Vendor assessments

Red Hat

Red Hat rating: Moderate. Red Hat's page for this CVE →

ProductStatusPlan or fix
Red Hat Enterprise Linux AI (RHEL AI)AffectedNo fix yet: Fix deferred

Timeline

  1. 2026-10-02 Threatist record created from CVE-2025-32381
  2. 2026-10-03 Alias added: GHSA-389x-67px-mjg3

References

Patch 2

Advisory 2

Other 2

  • TI-2025-36204 xgrammar vulnerable to denial of service by huge enum grammar CVSS 4.0MEDIUM 6.9
  • TI-2026-20232 xgrammar: Multi-layer nesting causes DoS CVSS 4.0HIGH 8.7
  • TI-2025-35692 XGrammar affected by Denial of Service by infinite recursion grammars CVSS 4.0HIGH 7.7

Sources

This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences