foundation-models-on-device

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides documentation for integrating on-device AI features using Swift, focusing on local execution and privacy.
  • [SAFE]: No network operations, data exfiltration, or hardcoded credentials were found in the analyzed file.
  • [SAFE]: The skill uses structured data patterns (@Generable) which reduce the risk associated with parsing unstructured model output.
  • [SAFE]: No obfuscation or malicious persistence mechanisms were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 03:45 PM