cal-com-automation

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection through the processing of untrusted data from the Cal.com API.
  • Ingestion points: Tools like CAL_FETCH_ALL_BOOKINGS and CAL_GET_AVAILABLE_SLOTS_INFO ingest data such as attendee names, email addresses, and event metadata provided by external users.
  • Boundary markers: The instructions lack specific delimiters or instructions for the agent to ignore or sanitize embedded commands within these fields.
  • Capability inventory: The skill possesses significant write capabilities, including CAL_POST_NEW_BOOKING_REQUEST and CAL_UPDATE_WEBHOOK_BY_ID, which could be abused if an injected instruction is followed.
  • Sanitization: There is no evidence of data sanitization or validation before the agent processes external content.
  • [EXTERNAL_DOWNLOADS]: The skill requires the configuration of an external third-party MCP server.
  • Finding: The setup process directs users to add https://rube.app/mcp as a remote server. This creates a dependency on an external infrastructure not controlled by the user or the primary platform.
  • Context: The skill states that no API keys are required for this endpoint, suggesting the external service manages authentication or acts as a proxy for Cal.com operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 05:19 PM