calendly-automation

Pass

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the Rube MCP server endpoint at https://rube.app/mcp, which is a recognized domain for MCP integration.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by processing external data from Calendly API endpoints. Ingestion points: External data enters the context through tools like CALENDLY_LIST_EVENTS and CALENDLY_LIST_EVENT_INVITEES as described in SKILL.md. Boundary markers: The instructions lack specific delimiters or instructions to ignore embedded commands in the retrieved data. Capability inventory: The skill includes impactful tools such as CALENDLY_CANCEL_EVENT, CALENDLY_REMOVE_USER_FROM_ORGANIZATION, and CALENDLY_CREATE_ORGANIZATION_INVITATION. Sanitization: No data sanitization or validation steps are defined for the information retrieved from the external service.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 25, 2026, 09:50 AM
Security Audit — agent-trust-hub — calendly-automation