apple-reminders
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill's primary function is to execute the 'remindctl' command-line interface to read from and write to the macOS Reminders database. This grants the agent the ability to run system commands and interact with local application data.
- [EXTERNAL_DOWNLOADS]: The skill requires the user to install a third-party utility from an external Homebrew tap ('brew install steipete/tap/remindctl'). This introduces a dependency on code maintained outside of the official agent or platform repositories.
- [INDIRECT_PROMPT_INJECTION]: The skill reads existing reminders (e.g., via 'remindctl today --json'), which creates a surface for indirect prompt injection if a reminder contains text intended to be interpreted as instructions by the agent.
- Ingestion points: Data retrieved from the system via 'remindctl' commands (SKILL.md).
- Boundary markers: Absent. The instructions do not provide delimiters or specific warnings to the agent to ignore instructions embedded within the reminder text.
- Capability inventory: Command execution via 'remindctl' for task management (SKILL.md).
- Sanitization: Absent. There is no evidence of filtering or validation of the data retrieved from the reminders database before it is processed by the agent.
Audit Metadata