mlc-ai/xgrammar · Security
XGrammar affected by Denial of Service by infinite recursion grammars
- GHSA ID
- GHSA-5cmr-4px5-23pc
- CVE ID
- CVE-2025-57809
- Severity
- high
- Published
- Updated
- CVSS
- 7.5 · CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
- CVSS v3
- 7.5 · CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
- CVSS v4
- 7.7 · CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:P
Description
Summary
This issue: http://github.com/mlc-ai/xgrammar/issues/250 should have it's own security advisory. Since several tools accept and pass user supplied grammars to xgrammar, and it is so easy to trigger it seems like a High.
CWEs
- CWE-674 · Uncontrolled Recursion
References
- https://github.com/mlc-ai/xgrammar/security/advisories/GHSA-5cmr-4px5-23pc ↗
- https://github.com/mlc-ai/xgrammar/issues/250 ↗
- https://github.com/mlc-ai/xgrammar/commit/b943feacb5a1caf4d39de8ec3bf7c7ce066dcee5 ↗
- https://nvd.nist.gov/vuln/detail/CVE-2025-57809 ↗
- https://github.com/advisories/GHSA-5cmr-4px5-23pc ↗