apple-reminders

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on the remindctl binary to perform all operations on Apple Reminders. It executes subcommands such as add, edit, list, complete, and delete via the system shell.
  • [PROMPT_INJECTION]: The instructions in SKILL.md direct the agent to use --force or --no-input flags when performing destructive actions like deleting reminders or lists. While this allows the agent to operate autonomously without waiting for interactive terminal prompts, it effectively bypasses standard user confirmation steps during automated workflows.
  • [SAFE]: The project follows security best practices for macOS development, including the use of Apple's EventKit framework for permission handling and data access. Sensitive signing credentials and API keys are managed through environment variables rather than being hardcoded in the source.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 10:26 AM