calendar-defrag
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from calendar events (titles, descriptions, attendees) which represents a potential attack surface for indirect prompt injection.
- Ingestion points: Calendar event metadata and descriptions retrieved via API (SKILL.md).
- Boundary markers: Absent; the instructions do not specify delimiters for meeting content.
- Capability inventory: Calendar API tool access for creating, moving, shortening, and declining events.
- Sanitization: Absent; however, the skill mandates a human-in-the-loop confirmation step for the entire execution plan before any actions are taken, which serves as a primary control.
- [DATA_EXPOSURE]: The skill calculates meeting costs based on attendee counts and durations. While this involves reading calendar metadata, the data is used locally for analysis and reporting to the user, and the skill explicitly forbids unauthorized changes or external data exfiltration.
- [COMMAND_EXECUTION]: The skill defines specific allowed actions for calendar tool interactions. These are limited to CRUD operations on the user's own calendar events and are strictly gated by human approval and validation steps.
Audit Metadata