apple-reminders

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the remindctl CLI tool to interact with the macOS Reminders database. It executes commands such as remindctl add, remindctl edit, and remindctl delete to perform task management operations.
  • [EXTERNAL_DOWNLOADS]: The skill documentation suggests installing the required dependency via Homebrew using brew install steipete/tap/remindctl or building from source using pnpm install. These are standard installation procedures for macOS developer tools.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it reads user-controlled data (reminder titles and notes) through remindctl commands.
  • Ingestion points: Data enters the agent's context when listing or viewing reminders (e.g., remindctl today).
  • Boundary markers: None identified in the provided instructions.
  • Capability inventory: The agent can execute shell commands (remindctl) and potentially other file system or network operations if those tools are available in its environment.
  • Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the Reminders database before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 10:38 PM