apple-reminders
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the macOS
osascriptutility to execute AppleScript commands. This is used to interact with the local Reminders application for creating, listing, and deleting tasks. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing data retrieved from the Reminders app.
- Ingestion points: Fetches task names, notes, and list names from the Apple Reminders database (SKILL.md).
- Boundary markers: No specific delimiters are used when the agent is instructed to read or process the output of the AppleScript commands.
- Capability inventory: The skill provides full CRUD (Create, Read, Update, Delete) capabilities over the user's reminders through shell execution of
osascript. - Sanitization: The skill relies on template interpolation. There is no evidence of sanitization or escaping logic for user-provided strings or data fetched from reminders before they are embedded into the AppleScript execution strings.
Audit Metadata