The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface by processing untrusted data from Calendly events and invitees. * Ingestion points: Data is ingested through tools like CALENDLY_LIST_EVENTS and CALENDLY_LIST_EVENT_INVITEES defined in SKILL.md. * Boundary markers: The instructions include a requirement to confirm with the user before performing destructive actions like CALENDLY_CANCEL_EVENT, providing a manual safety check, though formal prompt delimiters are not specified. * Capability inventory: The skill has access to sensitive operations including canceling events, inviting new users to the organization, and removing members. * Sanitization: No specific input sanitization or filtering of external Calendly content is mentioned.
[EXTERNAL_DOWNLOADS]: The skill references and requires a connection to an external MCP server at https://rube.app/mcp to function, which is the standard endpoint for the Rube toolkit.

calendly-automation