The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires a connection to an external MCP server endpoint at https://rube.app/mcp to function. This endpoint provides the underlying tool definitions and execution environment for the Calendly automation.
[DATA_EXFILTRATION]: The skill interacts with sensitive Calendly PII, including authenticated user URIs, organization identifiers, and invitee contact information (email addresses). This data is processed through the external Rube MCP server during normal operations.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its processing of untrusted external data provided by third parties.
Ingestion points: Data enters the agent's context through tools like CALENDLY_LIST_EVENTS and CALENDLY_LIST_EVENT_INVITEES, which fetch data controlled by meeting invitees (e.g., event reasons, names, or email metadata).
Boundary markers: There are no explicit instructions or delimiters used to prevent the agent from interpreting instructions that might be embedded in the Calendly API responses.
Capability inventory: The skill possesses significant capabilities, including CALENDLY_CANCEL_EVENT, CALENDLY_REMOVE_USER_FROM_ORGANIZATION, and CALENDLY_CREATE_ORGANIZATION_INVITATION, which could be targeted by an injection attack.
Sanitization: The instructions do not describe any sanitization or validation of the data retrieved from external APIs before it is used by the agent.

calendly-automation