Model-provider service interruption via slow grammar optimization
Published Sep 6, 2025 · Updated Sep 8, 2025
Denial of service in MLC XGrammar 0.1.23 allows remote attackers to interrupt model-provider service via a large grammar. Grammar.from_json_schema passes huge enums with repeated references into the 0.1.23 grammar optimizer, which processes them at a very low rate. The issue requires an integrating provider to accept attacker-controlled grammars, and the demonstrated consequence is minutes of parsing that delays normal work.
Summary
What happened
Denial of service in MLC XGrammar 0.1.23 allows remote attackers to interrupt model-provider service via a large grammar. Grammar.from_json_schema passes huge enums with repeated references into the 0.1.23 grammar optimizer, which processes them at a very low rate. The issue requires an integrating provider to accept attacker-controlled grammars, and the demonstrated consequence is minutes of parsing that delays normal work.
The record
- CVE
- CVE-2025-58446
- Published
- Sep 6, 2025
- Updated
- Sep 8, 2025
- Vendor
- MLC
- Product
- XGrammar
- Classifications
- CWE-770, T1499
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Sep 6, 2025CVE publishedPublication date reported by the CVE source.
- Sep 8, 2025Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion== 0.1.23, < 0.1.24
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- Large-enum JSON Schema reproducerproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo