The Agent Skills Directory

[PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection by processing untrusted data from external sources without explicit sanitization or boundary markers.
Ingestion points: The Meeting Preparation and Calendly Booking Handler workflows in SKILL.md extract data from calendar event descriptions, attendee profiles, and booking form responses.
Boundary markers: The templates do not utilize specific delimiters or instructions to prevent the agent from following commands embedded within the meeting descriptions or form answers.
Capability inventory: The skill has the capability to send messages via slack_notify and modify calendar data using calendar_update via the google-workspace-mcp server.
Sanitization: There is no evidence of input validation or escaping for the external content before it is used to generate notifications or update records.

calendar-automation