managing-calendly

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill exclusively communicates with the official Calendly API (api.calendly.com) to manage events and event types.
  • [SAFE]: Authentication is handled correctly by using an injected environment variable (CALENDLY_ACCESS_TOKEN) rather than hardcoding credentials.
  • [SAFE]: The skill presents a surface for indirect prompt injection because it ingests external data from Calendly (e.g., event names, user details, and cancellation reasons). This surface is documented as follows:
  • Ingestion points: Calendly API JSON responses processed in the Discovery and Analysis phases.
  • Boundary markers: None explicitly defined.
  • Capability inventory: Network requests (curl) to the official Calendly API.
  • Sanitization: Use of jq for field extraction limits the data volume passed to the agent's context, mitigating some risk. The risk is considered acceptable for the skill's intended purpose.
  • [SAFE]: No indicators of obfuscation, persistence mechanisms, privilege escalation, or malicious command execution were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 02:42 AM
Security Audit — agent-trust-hub — managing-calendly