cal-com-automation

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • SAFE (SAFE): No malicious patterns, exfiltration code, or prompt injection attempts were identified. The skill is entirely descriptive and focuses on scheduling workflows.\n- NO_CODE (SAFE): The skill is composed of a markdown instruction file and does not ship with any Python or Node.js code, reducing the local attack surface to zero.\n- Indirect Prompt Injection (LOW): (Vulnerability Surface Analysis)\n
  • Ingestion points: The skill processes untrusted data through tool parameters like attendee name, email, and metadata in the CAL_POST_NEW_BOOKING_REQUEST tool, and the subscriberUrl in webhook tools.\n
  • Boundary markers: There are no specific delimiters or instructional guards provided to separate user-provided data from system instructions.\n
  • Capability inventory: The skill enables creating bookings, managing webhooks (including delete/update), and managing teams.\n
  • Sanitization: No sanitization or validation of external input is mentioned or performed within the prompt logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:08 PM