apple-reminders
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
remindctlcommand-line utility to perform operations on the Apple Reminders database. This is the primary function of the skill. - [EXTERNAL_DOWNLOADS]: The skill metadata includes installation instructions to fetch and install the
remindctlformula from a GitHub-hosted Homebrew tap (steipete/tap/remindctl). - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes data (reminder titles and notes) that could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Data enters the agent context via
remindctloutput (e.g.,remindctl today,remindctl list). - Boundary markers: None identified; external content is not explicitly delimited with warnings to ignore embedded instructions.
- Capability inventory: The skill has the capability to execute subprocesses via the
remindctlbinary to create, modify, or delete reminders. - Sanitization: No evidence of sanitization or filtering of reminder content before it is processed by the agent.
Audit Metadata