calendly-automation
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious code or instructions were detected. The skill is entirely instructional and utilizes established tools from a well-known service provider.
- [EXTERNAL_DOWNLOADS]: The skill references an external Model Context Protocol (MCP) server at https://rube.app/mcp to provide its core functionality.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface where the agent processes data from Calendly events and invitees that may be controlled by third parties. 1. Ingestion points: Calendly event details and invitee metadata retrieved via CALENDLY_LIST_EVENTS and CALENDLY_GET_EVENT. 2. Boundary markers: Absent in the provided templates. 3. Capability inventory: Destructive actions such as CALENDLY_CANCEL_EVENT and CALENDLY_REMOVE_USER_FROM_ORGANIZATION. 4. Sanitization: The skill mitigates this risk by explicitly instructing the agent to get human confirmation before executing any irreversible cancellation or organization management tasks.
Audit Metadata