model-security-scanning
Installation
SKILL.md
Model Security Scanning in Inference Engines
Security Recommendation
Inference engines SHOULD scan models for malicious elements before loading them. This is a defense-in-depth control that complements signature verification.
Threats Detected by Scanning
| Threat | Description |
|---|---|
| Malicious code in weights | Some weight formats (e.g., Python pickle) can embed arbitrary executable code |
| Backdoored models | Models with hidden behaviors triggered by specific inputs |
| Embedded scripts | Configuration files or metadata containing executable payloads |
| Unsafe serialization formats | Formats that execute code during deserialization |
Unsafe Weight Formats
The inference engine SHOULD advise against or refuse to load weight formats that can include malicious code: