apple-reminders
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
remindctlCLI utility to interact directly with the macOS Reminders database. - [EXTERNAL_DOWNLOADS]: Recommends the installation of a third-party tool via Homebrew from the
steipete/tap/remindctlrepository. - [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection as it processes data from reminders that could contain instructions intended to influence the agent's behavior. 1. Ingestion points: Reminder titles, notes, and list names retrieved via
remindctl. 2. Boundary markers: Absent; there are no instructions to use delimiters or ignore embedded commands in the reminder data. 3. Capability inventory: The agent can list, add, complete, and delete reminders through CLI calls. 4. Sanitization: Absent; the skill does not specify any validation or filtering of the content retrieved from the system.
Audit Metadata