axiom-foundation-models-ref
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a static documentation resource. It contains Swift code snippets intended for developer education rather than execution within the agent environment.
- [PROMPT_INJECTION]: No injection or bypass patterns were detected. The content includes proactive security guidance for developers, specifically advising on the separation of instructions and user prompts to prevent injection attacks.
- [DATA_EXFILTRATION]: No hardcoded credentials, access to sensitive file paths, or unauthorized network operations were found. References to system frameworks (e.g., WeatherKit, MapKit) are standard for the documented API.
- [REMOTE_CODE_EXECUTION]: There are no patterns for downloading or executing remote scripts or packages. The skill does not contain any shell commands or dynamic execution logic.
Audit Metadata