cal-com-automation

Pass

Audited by Gen Agent Trust Hub on Apr 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection via the Cal.com API data it processes.
  • Ingestion points: Data entering the agent context via CAL_FETCH_ALL_BOOKINGS and CAL_GET_AVAILABLE_SLOTS_INFO which contain attendee names, emails, and metadata.
  • Boundary markers: Absent; the instructions do not provide delimiters or directives to treat external data as untrusted.
  • Capability inventory: The skill utilizes tools capable of modifying bookings (CAL_POST_NEW_BOOKING_REQUEST), configuring webhooks (CAL_UPDATE_WEBHOOK_BY_ID), and managing teams (CAL_CREATE_TEAM_IN_ORGANIZATION).
  • Sanitization: No sanitization, validation, or escaping protocols are specified for data retrieved from external Cal.com accounts.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 25, 2026, 11:30 PM