apple-remind-me
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes the
remindctlbinary and the systemdateutility to create, list, and modify reminders. These operations are consistent with the skill's primary purpose. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection.
- Ingestion points: The
list-reminders.shscript reads reminder titles and notes from the Apple Reminders database and presents them to the agent. - Boundary markers: No delimiters or warnings are used to distinguish retrieved reminder content from the agent's instructions.
- Capability inventory: The skill possesses the ability to create, delete, and modify reminder entries via shell scripts.
- Sanitization: Reminder content is processed as JSON but is not sanitized for instruction-like patterns before being displayed to the agent.
Audit Metadata