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
Risk Level
SAFE
Analyzed
Mar 5, 2026, 11:54 AM