Log in Start free

Vulnerability · Published Mar 5, 2026 · Assigned by GitHub_M

CVE-2026-25048xgrammar: Multi-layer nesting causes DoS

High 7.5

In plain English

A high-severity security flaw in xgrammar from mlc-ai. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 1.3% (higher than 71% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)7.5High
Exploit odds (30 days)1.3%top 29.0% of all CVEs
Exploited in the wildNo reportsCISA SSVC: none
Attack toolingNoneno public tooling known

Official description

xgrammar is an open-source library for efficient, flexible, and portable structured generation. Prior to version 0.1.32, the multi-level nested syntax caused a segmentation fault (core dumped). This issue has been patched in version 0.1.32.

Affected packages & fixed versions

EcosystemPackageFixed inAdvisory
PyPIxgrammar0.1.32GHSA-7rgv-gqhr-fxg3
PyPIxgrammar0.1.32PYSEC-2026-2322

Affected products (as reported)

VendorProductVersions
mlc-ai xgrammar < 0.1.32

Weakness: CWE-674 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References