apple-shortcuts

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed for the generation and analysis of Apple Shortcut files (plists). All included Python scripts (validate-shortcut.py, inspect-shortcut.py, list-native-actions.py, list-app-intents.py, find-action-identifier.py, and diff-actions.py) utilize only the Python standard library and perform local file operations consistent with their stated purpose.
  • [EXTERNAL_DOWNLOADS]: The skill references legitimate, well-known community resources and documentation for Apple Shortcuts development, such as repositories from Sindre Sorhus and Simon Støvring. These references are provided for user information and do not involve automated or unsafe downloads by the agent.
  • [COMMAND_EXECUTION]: The provided Python utilities scan application directories (e.g., /Applications) and system frameworks (e.g., /System/Library/PrivateFrameworks/WorkflowKit.framework) to extract action metadata. This behavior is restricted to reading configuration files and Info.plists to provide accurate identifier mappings for the user.
  • [DATA_EXFILTRATION]: No evidence of credential harvesting or data exfiltration was found. The skill follows best practices for secret management by instructing users to use 'Import Questions' for API tokens, ensuring sensitive values are supplied by the end-user at the time of shortcut import.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 02:50 PM
Security Audit — agent-trust-hub — apple-shortcuts