apple-reminders

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on the remindctl command-line utility to interact with the macOS Reminders system, performing actions such as listing, adding, and completing tasks through shell execution.
  • [EXTERNAL_DOWNLOADS]: The instructions specify installing a third-party dependency via Homebrew (steipete/tap/remindctl). This involves fetching and installing software from an external repository managed by an individual developer.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data by reading existing reminders from the user's system. If a reminder contains adversarial instructions, it could potentially influence the agent's behavior.
  • Ingestion points: The agent reads reminder titles and list names via remindctl (SKILL.md).
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the reminder text as data only.
  • Capability inventory: The skill has the capability to execute shell commands (remindctl).
  • Sanitization: The skill does not include specific sanitization or validation steps for the content retrieved from reminders.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 07:01 PM
Security Audit — agent-trust-hub — apple-reminders