Code execution via ungated auto_map module loading
Published Jan 21, 2026 · Updated Jan 21, 2026
Code injection in vLLM 0.10.1 through 0.13.0 allows remote attackers to execute code by supplying a malicious model repository. During startup, registry.py resolves auto_map entries with try_get_class_from_dynamic_module, which executes referenced Python without enforcing trust_remote_code. Exploitation requires control over the configured local path or Hugging Face repository before model loading; API access alone cannot reach the path.
Summary
What happened
Code injection in vLLM 0.10.1 through 0.13.0 allows remote attackers to execute code by supplying a malicious model repository. During startup, registry.py resolves auto_map entries with try_get_class_from_dynamic_module, which executes referenced Python without enforcing trust_remote_code. Exploitation requires control over the configured local path or Hugging Face repository before model loading; API access alone cannot reach the path.
The record
- CVE
- CVE-2026-22807
- Published
- Jan 21, 2026
- Updated
- Jan 21, 2026
- Vendor
- vLLM Project
- Product
- vLLM
- Classifications
- CWE-94, T1204.002
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jan 21, 2026CVE publishedPublication date reported by the CVE source.
- Jan 21, 2026Record 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=>= 0.10.1, < 0.14.0
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
No public exploit references are available in this record.
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