calendly-automation

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and processes Calendly content (e.g., CALENDLY_LIST_EVENTS, CALENDLY_LIST_EVENT_INVITEES, CALENDLY_GET_EVENT_INVITEE and related endpoints) — user/invitee data from the Calendly API is untrusted/user-generated and is read by the agent to make decisions and perform actions (e.g., selecting or cancelling events, creating links), which enables indirect injection risk.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). Yes — the skill requires connecting to the Rube MCP endpoint at https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS) to fetch current tool schemas that directly determine the agent's available tools/instructions, so this external URL can control agent behavior.