Skills
skills/bighardperson/computer-science-skills-collection/apple-reminders/Gen Agent Trust Hub

apple-reminders

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install a CLI tool from a third-party Homebrew tap (steipete/tap/remindctl). This introduces a dependency on external code maintained by a third-party developer.
  • [COMMAND_EXECUTION]: The skill operates by executing the remindctl binary with various shell arguments to interact with the system's reminders database.
  • [PROMPT_INJECTION]: The skill reads reminder content which creates an indirect prompt injection surface. If a reminder contains malicious instructions, the agent might inadvertently execute them while processing the reminder's text.
  • Ingestion points: Outputs from remindctl commands like today or all.
  • Boundary markers: None specified.
  • Capability inventory: CLI execution via shell.
  • Sanitization: None specified.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 10:48 AM
Security Audit — agent-trust-hub — apple-reminders