xgrammar vulnerable to denial of service by huge enum grammar
Priority HIGH 70CWE-770Published · Updated
Key facts
- Attack vector
- Network
- Privileges required
- None
- User interaction
- None
- Attack complexity
- Low
- Attack requirements
- None
- Impact type
- Denial of service
- Confidentiality · integrity · availability
- None · None · Low
- Fix status
- Fixed
Attack profile from CVSS 4.0 · CNA. Fix status from CNA and GitHub. Impact type from CWE-770.
Summary
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.
Why it matters now
Exploitation Proof of concept CISA SSVC · not in CISA KEV
EPSS 0.00619 49th percentileScored 2026-11-07
Public exploit Yes 1 exploit referenceTagged by NVD
Fix Fixed xgrammar (PyPI): 0.1.24
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- Poc
- Automatable
- Yes
- Technical impact
- Partial
The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.
Affected products
| Vendor | Product | Affected versions | Fixed in | Status | Source |
|---|---|---|---|---|---|
| mlc-ai | xgrammar | = 0.1.23, < 0.1.24 | — | No fix listed | CNA |
| — | xgrammar (PyPI) | 0.1.23 to before 0.1.24 | 0.1.24 | Patch available | GHSA-9q5r-wfvf-rr7f |
- xgrammar Vendormlc-ai Affected = 0.1.23, < 0.1.24 Fixed in — No fix listed CNA
- xgrammar (PyPI) Vendor— Affected 0.1.23 to before 0.1.24 Fixed in 0.1.24 Patch available GHSA-9q5r-wfvf-rr7f
Remediation
- Fix · GHSA-9q5r-wfvf-rr7f xgrammar (PyPI) Fixed in 0.1.24 Advisory →
Vendor assessments
Red Hat
Red Hat rating: Moderate. Red Hat's page for this CVE →
Not affected: 2 products
- Red Hat AI Inference Server
- Red Hat Enterprise Linux AI (RHEL AI)
Timeline
- 2026-10-02 Threatist record created from CVE-2025-58446
- 2026-10-03 Alias added: GHSA-9q5r-wfvf-rr7f
References
More mlc-ai Xgrammar vulnerabilities
- 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
- TI-2025-23460 Denial of Service by abusing xgrammar unbounded cache in memory CVSS 3.1MEDIUM 6.5
Sources
- CVE-2025-58446 · CVE Program
- CVE-2025-58446 · NVD
- FIRST EPSS
- GHSA-9q5r-wfvf-rr7f · GitHub Advisory Database · CC BY 4.0
- CVE-2025-58446 · Red Hat security data · CC BY 4.0
This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences