eventkit
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides methods to read data from the user's calendar and reminders, which are external sources that can contain untrusted content.
- Ingestion points:
fetchEventsandfetchIncompleteRemindersinSKILL.md. - Boundary markers: The instructions do not include prompt delimiters or warnings to ignore instructions embedded in the calendar data.
- Capability inventory: The skill allows full CRUD access to events and reminders via the
EKEventStoreAPI. - Sanitization: No data validation or sanitization of ingested event titles, descriptions, or reminder notes is present in the provided code snippets.
- [SAFE]: The skill correctly demonstrates how to request user authorization using the granular, asynchronous methods required for iOS 17 and later, ensuring the agent follows platform security protocols for sensitive user data access.
Audit Metadata