skills/zapabob/skills/apple-reminders/Gen Agent Trust Hub

apple-reminders

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the remindctl command-line utility to perform operations on the macOS Reminders database, such as adding, editing, completing, and deleting tasks.
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install an external dependency via a third-party Homebrew tap (steipete/tap/remindctl) to enable its core functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill reads external data from the Reminders database, which could potentially contain malicious instructions embedded by an attacker in reminder titles or notes.
  • Ingestion points: Data enters the context via remindctl, remindctl list, and remindctl today --json commands.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore embedded commands within the ingested reminder data.
  • Capability inventory: The skill has the capability to execute shell commands (remindctl) and write/delete data in the local Reminders database.
  • Sanitization: There is no explicit sanitization or filtering of the content retrieved from the Reminders app before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 12:07 PM