mlc-ai vulnerabilities
Recent CVEs affecting mlc-ai products. 4 tracked.
mlc-ai has 4 tracked vulnerabilities, 0 critical. A fixed release or vendor patch exists for 3. Most recent: 2026-03-05. Highest priority: CVE-2026-25048 (score 53/100).
- CVE-2026-25048 HIGH 7.5 UPGRADE xgrammar is an open-source library for efficient, flexible, and portable structured generation
- CVE-2025-58446 HIGH 7.5 DOWNGRADE xgrammar is an open-source library for efficient, flexible, and portable structured generation
- CVE-2025-57809 HIGH 7.5 UPGRADE XGrammar is an open-source library for efficient, flexible, and portable structured generation
- CVE-2025-32381 MEDIUM 6.5 UPGRADE XGrammar is an open-source library for efficient, flexible, and portable structured generation
FAQ
How do I fix mlc-ai vulnerabilities?
Open the CVE for your version, check the affected range, then follow the listed action: upgrade to the fixed release, or downgrade or mitigate if no fix exists yet. Commands for each OS are shown on every CVE page.
Is mlc-ai being exploited right now?
None of the tracked mlc-ai CVEs are on the CISA Known Exploited Vulnerabilities list at the moment. This is checked every 20 minutes.
Which mlc-ai CVE should I patch first?
CVE-2026-25048 currently ranks highest (53/100): xgrammar is an open-source library for efficient, flexible, and portable structured generation.