apple-reminders

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill directs the user to install an external tool via brew install steipete/tap/remindctl. This is a third-party dependency necessary for the skill's functionality.
  • [COMMAND_EXECUTION]: The skill relies on executing the remindctl command-line utility to perform its core functions, including listing and modifying reminder data on the host system.
  • [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection as it reads and processes arbitrary text from the user's reminders list.
  • Ingestion points: Data retrieved from the Reminders database via remindctl (SKILL.md).
  • Boundary markers: Absent; the agent is not instructed to treat reminder content as untrusted data.
  • Capability inventory: Local command execution and data modification capabilities via remindctl (SKILL.md).
  • Sanitization: No sanitization or validation of the retrieved reminder content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 07:07 AM