apple-reminders

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the remindctl utility from a GitHub-hosted Homebrew tap (steipete/tap/remindctl). This is a standard installation method for macOS developer tools.
  • [COMMAND_EXECUTION]: The skill primarily operates by executing remindctl shell commands (e.g., remindctl add, remindctl list, remindctl complete) to interact with the local macOS Reminders database. These commands are executed within the scope of the agent's environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from the Apple Reminders application, which serves as a potential vector for indirect prompt injection.
  • Ingestion points: Data is ingested via remindctl command outputs when viewing today's tasks, lists, or specific reminders (in SKILL.md).
  • Boundary markers: The instructions do not specify any delimiters or safety warnings to ignore instructions embedded within reminder text.
  • Capability inventory: The skill possesses the capability to execute shell commands (remindctl) and write to the Reminders database.
  • Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the reminders before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 12:09 AM