What’s Vulnerable › Vulnerabilities

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

• Severity: medium (CVSS 6.5 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.5% probability of exploitation in the next 30 days
• Public exploit or detection template: none known
• Published: 2025-04-09 · updated 2026-06-17
• Weakness: CWE-770

Description

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 unbounded, a system making use of xgrammar can be abused to fill up a host's memory and case a denial of service. For example, sending many small requests to an LLM inference server with unique JSON schemas would eventually cause this denial of service to occur. This vulnerability is fixed in 0.1.18.

Affected products

• mlc-ai xgrammar: before 0.1.18 — fixed in 0.1.18

How to fix

Upgrade to a fixed version: mlc-ai xgrammar 0.1.18. Check the vendor advisory for mitigations.

References

• https://github.com/mlc-ai/xgrammar/pull/243
• https://github.com/mlc-ai/xgrammar/security/advisories/GHSA-389x-67px-mjg3
• https://github.com/vllm-project/vllm/pull/16283

Get alerted when CVE-2025-32381 or the next vulnerability affects your stack