Vulnerability · Published Apr 9, 2025 · Assigned by GitHub_M

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

Medium 6.5

In plain English

A medium-severity resource allocation without limits 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 0.5% (higher than 44% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)6.5Medium

Exploit odds (30 days)0.5%top 55.8% 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 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 packages & fixed versions

Ecosystem	Package	Fixed in	Advisory
PyPI	xgrammar	0.1.18	GHSA-389x-67px-mjg3
PyPI	xgrammar	0.1.18	PYSEC-2025-235

Affected products (as reported)

Vendor	Product	Versions
mlc-ai	xgrammar	< 0.1.18

Weakness: CWE-770 · Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

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