Skip to content

Vendor

mlc-ai vulnerabilities

4 published CVES affecting mlc-ai, from public sources (CVE.org, NVD, CISA KEV, FIRST EPSS, OSV).

Total
4
Critical
0
High
2
Medium
2
Low
0
Unscored
0
CISA KEV
0
Atom feed of mlc-ai alerts

Products

Latest mlc-ai CVEs

Newest publication first

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

    Published
    HighCVSS 8.7 EPSS 1.3%

    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.

  2. CVE-2025-58446 xgrammar vulnerable to denial of service by huge enum grammar

    Published
    MediumCVSS 6.9 EPSS 0.62%

    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 0.1.2...

  4. CVE-2025-32381 Denial of Service by abusing xgrammar unbounded cache in memory

    Published
    MediumCVSS 6.5 EPSS 0.52%

    XGrammar is an open-source library for efficient, flexible, and portable structured generation. Prior to 0.1.18, Xgrammar includes a cache for compiled grammars to increase performance with repeated use of the same grammar. This cache is held in memory. Since the cache is unbound...

Sources: CVE.org, NVD, CISA KEV, FIRST EPSS, OSV and public exploit-reference metadata. Product matching comes from the published CVE records. A proof-of-concept means public code exists; it is not evidence of exploitation.