axiom-foundation-models-ref
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a static documentation reference for a Swift-based machine learning framework. No executable code or shell scripts are included.
- [SAFE]: The documentation explicitly identifies prompt injection as a risk and provides architectural guidance to prevent it (e.g., instructing developers to never interpolate untrusted input into system instructions).
- [SAFE]: No obfuscated content, hardcoded credentials, or network exfiltration patterns were found in the markdown or metadata files.
- [SAFE]: All code examples use standard, legitimate system APIs (e.g., CoreLocation, WeatherKit, MapKit).
Audit Metadata