CVE-2025-32381
6.5 · MEDIUMOverview
CVE-2025-32381 is a medium-severity vulnerability affecting mlc-ai xgrammar. It was published on April 9, 2025 and has a CVSS 3.1 base score of 6.5 (MEDIUM).
This vulnerability has a CVSS 3.1 base score of 6.5, rated MEDIUM. It can be exploited remotely over the network. Some level of privileges is required for exploitation.
Technical 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.
Remediation
Check the references section for vendor advisories and patches from mlc-ai. Update xgrammar to the latest patched version. If immediate patching is not possible, review the CVSS vector to understand the attack surface and apply compensating controls such as network segmentation or access restrictions.
Affected Products
| Vendor | Product | Versions | Status |
|---|---|---|---|
| mlc-ai | xgrammar | >= 0, < 0.1.18 | Affected |
Frequently Asked Questions
What is CVE-2025-32381?
CVE-2025-32381 is a medium-severity vulnerability affecting mlc-ai xgrammar. It was published on April 9, 2025 and has a CVSS 3.1 base score of 6.5 (MEDIUM).
How severe is CVE-2025-32381?
This vulnerability has a CVSS 3.1 base score of 6.5, rated MEDIUM. It can be exploited remotely over the network. Some level of privileges is required for exploitation.
How do I fix or remediate CVE-2025-32381?
Check the references section for vendor advisories and patches from mlc-ai. Update xgrammar to the latest patched version. If immediate patching is not possible, review the CVSS vector to understand the attack surface and apply compensating controls such as network segmentation or access restrictions.
How can CyberStrike help with CVE-2025-32381?
CyberStrike's AI-powered security agents can automatically detect CVE-2025-32381 across your infrastructure using autonomous pentesting, DAST scanning, and HackBrowser. The platform continuously monitors for known vulnerabilities and provides actionable remediation guidance prioritized by real-world exploitability.
How CyberStrike Helps
AI agents map your attack surface to find vulnerabilities like this one.
Automated penetration testing that runs continuously, not just quarterly.
AI-driven PR review catches vulnerable dependencies before they ship.
Browser-based exploitation validates findings with real proof-of-concept.
Related MEDIUM CVEs from 2025
View all →OpenID Connect Core through 1.0 errata set 2 allows audience injection in certain situations. When t
In certain IETF OAuth 2.0-related specifications, when the JSON Web Token Profile for OAuth 2.0 Clie
Missing Critical Step in Authentication vulnerability in Elfatek Elektronics ANKA JPD-00028 allows A
In version v0.3.8 of open-webui/open-webui, sensitive actions such as deleting and resetting are per
Parse Server is an open source backend that can be deployed to any infrastructure that can run Node.
Dell Client Platform BIOS contains a Stack-based Buffer Overflow Vulnerability. A high privileged at
In JetBrains Toolbox App before 2.6 unencrypted credential transmission during SSH authentication wa
VMware NSX contains a stored Cross-Site Scripting (XSS) vulnerability in the gateway firewall due to
Authentication vulnerability in the distributed collaboration framework module Impact: Successful ex
SAPCAR allows an attacker logged in with high privileges to create a malicious SAR archive in SAPCAR
SAPCAR allows an attacker logged in with high privileges to override the permissions of the current
DSpace open source software is a repository application which provides durable access to digital res