foundation-models

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely educational, providing implementation guides for Apple's on-device LLM framework (FoundationModels).
  • [SAFE]: Prompt engineering sections include specific 'Safety' components, encouraging developers to implement boundaries such as declining medical advice.
  • [SAFE]: Code snippets demonstrate standard SwiftUI and Swift implementation patterns for session management, tool calling, and structured output.
  • [SAFE]: All external references point to official Apple developer documentation and reputable technical blogs. No suspicious network operations or unauthorized data access patterns were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 05:18 PM
Security Audit — agent-trust-hub — foundation-models