Advisory

GHSA-389x-67px-mjg3

Also known as: CVE-2025-32381, PYSEC-2025-235

Summary

xgrammar Vulnerable to Denial of Service (DoS) by abusing unbounded cache in memory

Details

Summary

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.

Details

The fix is to add a limit to the cache size. This was done in https://github.com/mlc-ai/xgrammar/pull/243

An example of making use of the new cache size limit can be found in vLLM here: https://github.com/vllm-project/vllm/pull/16283

Impact

Any system making use of Xgrammar and taking requests as input from potentially untrusted parties would be vulnerable to this denial of service issue.

Severity

Medium Basis: The source's own band: MODERATE

Dates

Published
2025-04-09 13:08 UTC
Modified
2026-09-10 03:50 UTC

Affected packages and fixes

xgrammar

PyPI · All systems

Affected

  • introduced 0, fixed 0.1.18 (ecosystem)

Fixed versions

0.1.18

Fix

  • Fixed version 0.1.18
    pip install --upgrade xgrammar==0.1.18

Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.

Check your own computer: guard packages check

View this record on OSV.dev

Source

Source: GitHub Advisory Database (reviewed advisories) · CC BY 4.0

Sources & licences