XGrammar affected by Denial of Service by infinite recursion grammars
Priority LOW 34CWE-674Published · 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 · High
- Fix status
- Partial Red Hat: 1 fixed, 1 without a fix
Attack profile from CVSS 4.0 · CNA. Fix status from CNA, GitHub and Red Hat. Impact type from CWE-674.
Summary
XGrammar is an open-source library for efficient, flexible, and portable structured generation. Prior to version 0.1.21, XGrammar has an infinite recursion issue in the grammar. This issue has been resolved in version 0.1.21.
Why it matters now
Exploitation None reported CISA SSVC · not in CISA KEV
EPSS 0.00485 41st percentileScored 2026-11-07
Public exploit Yes 1 exploit referenceTagged by NVD
Fix Partial xgrammar (mlc-ai): 0.1.21xgrammar (PyPI): 0.1.21Red Hat: 10 advisoriesRed Hat: 1 fixed, 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
| Vendor | Product | Affected versions | Fixed in | Status | Source |
|---|---|---|---|---|---|
| mlc-ai | xgrammar | before 0.1.21 | 0.1.21 | Patch available | CNA |
| — | xgrammar (PyPI) | before 0.1.21 | 0.1.21 | Patch available | GHSA-5cmr-4px5-23pc |
- xgrammar Vendormlc-ai Affected before 0.1.21 Fixed in 0.1.21 Patch available CNA
- xgrammar (PyPI) Vendor— Affected before 0.1.21 Fixed in 0.1.21 Patch available GHSA-5cmr-4px5-23pc
Remediation
- Fix · CNA xgrammar (mlc-ai) Fixed in 0.1.21
- Fix · GHSA-5cmr-4px5-23pc xgrammar (PyPI) Fixed in 0.1.21 Advisory →
Red Hat 10 advisories
- RHSA-2025:19430 Released 2025-11-03 · Red Hat rating ImportantRed Hat Enterprise Linux AI 1.5 (NVIDIA)
- Red Hat Enterprise Linux AI 1.5 registry.redhat.io/rhelai1/bootc-azure-nvidia-rhel9
- RHSA-2025:19429 Released 2025-11-03 · Red Hat rating ImportantRed Hat Enterprise Linux AI 1.5 (NVIDIA)
- Red Hat Enterprise Linux AI 1.5 registry.redhat.io/rhelai1/bootc-aws-nvidia-rhel9
- RHSA-2025:19428 Released 2025-11-03 · Red Hat rating ImportantRed Hat Enterprise Linux AI 1.5 (NVIDIA)
- Red Hat Enterprise Linux AI 1.5 registry.redhat.io/rhelai1/bootc-nvidia-rhel9
Show 7 more Red Hat advisories
- RHSA-2025:19427 Released 2025-11-03 · Red Hat rating ImportantRed Hat Enterprise Linux AI 1.5 (AMD)
- Red Hat Enterprise Linux AI 1.5 registry.redhat.io/rhelai1/bootc-amd-rhel9
- RHSA-2025:19426 Released 2025-11-03 · Red Hat rating ImportantRed Hat Enterprise Linux AI 1.5 (NVIDIA)
- Red Hat Enterprise Linux AI 1.5 registry.redhat.io/rhelai1/bootc-gcp-nvidia-rhel9
- RHSA-2025:19425 Released 2025-11-03 · Red Hat rating ImportantRed Hat Enterprise Linux AI 1.5 (AMD)
- Red Hat Enterprise Linux AI 1.5 registry.redhat.io/rhelai1/instructlab-amd-rhel9
- RHSA-2025:19424 Released 2025-11-03 · Red Hat rating ImportantRed Hat Enterprise Linux AI 1.5 (AMD)
- Red Hat Enterprise Linux AI 1.5 registry.redhat.io/rhelai1/bootc-azure-amd-rhel9
- RHSA-2025:19423 Released 2025-11-03 · Red Hat rating ImportantRed Hat Enterprise Linux AI 1.5 (NVIDIA)
- Red Hat Enterprise Linux AI 1.5 registry.redhat.io/rhelai1/instructlab-nvidia-rhel9
- RHSA-2025:19422 Released 2025-11-03 · Red Hat rating ImportantRed Hat Enterprise Linux AI 1.5 (Intel Gaudi)
- Red Hat Enterprise Linux AI 1.5 registry.redhat.io/rhelai1/bootc-intel-rhel9
- RHSA-2025:19421 Released 2025-11-03 · Red Hat rating ImportantRed Hat Enterprise Linux AI 1.5 (Intel Gaudi)
- Red Hat Enterprise Linux AI 1.5 registry.redhat.io/rhelai1/instructlab-intel-rhel9
Vendor assessments
Red Hat
Red Hat rating: Important. Red Hat's page for this CVE →
| Product | Status | Plan or fix |
|---|---|---|
| Red Hat AI Inference Server | Affected | No fix yet |
| Red Hat Enterprise Linux AI 1.5 | Fixed | RHSA-2025:19421, RHSA-2025:19422, RHSA-2025:19423, RHSA-2025:19424, RHSA-2025:19425, RHSA-2025:19426, RHSA-2025:19427, RHSA-2025:19428, RHSA-2025:19429, RHSA-2025:19430 |
Timeline
- 2026-10-02 Threatist record created from CVE-2025-57809
- 2026-10-03 Alias added: GHSA-5cmr-4px5-23pc
References
Advisory 2
More mlc-ai Xgrammar vulnerabilities
- 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-2025-23460 Denial of Service by abusing xgrammar unbounded cache in memory CVSS 3.1MEDIUM 6.5
Sources
- CVE-2025-57809 · CVE Program
- CVE-2025-57809 · NVD
- FIRST EPSS
- GHSA-5cmr-4px5-23pc · GitHub Advisory Database · CC BY 4.0
- CVE-2025-57809 · 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