NIST deprecates RSA-2048 from 2030. Find every one of them before attackers do.
🐍
🐍 PyPI
Not in CISA KEV
MEDIUM severity

CVE-2025-32381 — xgrammar

MEDIUMFix: mlc-ai/xgrammar#243

CVE-2025-32381 is a medium-severity (CVSS 6.5) CWE-770 vulnerability in xgrammar. A fix is available for xgrammar — see the affected versions and patch details below.

Denial of Service by abusing xgrammar unbounded cache in memory

Also known asGHSA-389x-67px-mjg3PYSEC-2025-235
Published
Updated
Affected
1 pkg
Patched
1 / 1
Exploits
None indexed
Exploitation data as of Nov 10, 2026 · OSV.dev, NVD, FIRST.org (EPSS)

Exploitation Status

No confirmed exploitation observed yet

  • CISA’s own triage has not observed active exploitation or public proof-of-concept code for this CVE as of its last assessment.

Exploitation and automatability from CISA’s SSVC triage for CVE-2025-32381.

EPSS Exploitation Probability

via FIRST.org ↗
0.5%probability of exploitation in next 30 days
Lower Risk+0.01%
Lower risk than most CVEs44th percentile — riskier than 44% of all scored CVEsHighest risk
0.00%0.34%0.68%1.02%0.3%0.5%May 26Sep 26Nov 26

Probability of exploitation in the next 30 days, from FIRST.org EPSS.

How urgent is this, really

Where this sits among everything scored

Real-World Exposure

1 pkg affected
🐍xgrammar

Real-time download stats are indexed for npm and PyPI packages. This vulnerability affects PyPI packages — download data is not available via public APIs for these ecosystems.

Description

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.

Affected Packages

1 total 1 fixed
EcosystemPackageVulnerable rangeFix
🐍PyPIxgrammarall versions0.1.18pip install --upgrade 'xgrammar==0.1.18'

Affected Products

1 product · 1 configurations
Application
xgrammarmlc-ai
< 0.1.18
range

Detection & mitigation playbook

Open-source dependency
  1. Detect

    Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for xgrammar, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.

  2. Fix

    Update xgrammar to 0.1.18 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2025-32381 is resolved across your whole dependency graph.

  3. Workarounds

    Cap what an attacker can consume: apply request size, rate and timeout limits in front of the affected component, and run it with memory and CPU limits so exhaustion degrades one worker rather than the whole service.

Fixing This On Your OS

If you run this on a Linux distribution, patch through your package manager against the distro's own security advisory below — it tracks the exact backported fix for your release, which can ship on a different timeline (and sometimes a different severity) than the upstream project.

Red HatModerate
Workaround published by Red Hat
Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base or stability.
Source: Red Hat security advisory for CVE-2025-32381 (CC BY 4.0)

Frequently Asked Questions

### 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 s
O3 Security · Impact-Aware SCA

Is CVE-2025-32381 in your dependencies?

Find it across PyPI, including transitive dependencies.

CVE-2025-32381: xgrammar DoS — Fixed in 0.1.18