apple-reminders

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill directs the installation of the remindctl utility from a third-party Homebrew tap (steipete/tap/remindctl) and references building the tool from source using pnpm.
  • [COMMAND_EXECUTION]: The skill's primary functionality relies on executing the remindctl binary via the shell to interact with the macOS Reminders database.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes untrusted data.
  • Ingestion points: The agent ingests data from the local Apple Reminders database through commands like remindctl today or remindctl all.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between its own instructions and the content retrieved from reminders.
  • Capability inventory: The skill has the ability to read, create, modify, and delete reminders, and executes shell commands via the remindctl binary.
  • Sanitization: The skill does not implement sanitization or validation of the text content within reminders before it is returned to the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 04:19 PM