calendly-automation

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

• Third-party content exposure detected (high risk: 0.70). The skill's required workflows (e.g., CALENDLY_LIST_EVENTS, CALENDLY_GET_EVENT, CALENDLY_LIST_EVENT_INVITEES as documented in SKILL.md) explicitly fetch and interpret data from the third‑party Calendly API (https://api.calendly.com) — user-generated event/invitee content is read and used to drive actions like cancellations, invitations, and scheduling, so untrusted third‑party content can materially influence tool use and decisions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires configuring and calling the remote MCP endpoint https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS) to fetch current tool schemas that the agent must use to drive its behavior, so this external URL directly influences agent prompts/instructions.