clickup-automation

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

• Third-party content exposure detected (high risk: 0.70). The required workflow is described as calling ClickUp toolkit tools (e.g., CLICKUP_GET_TASK, CLICKUP_GET_TASKS, CLICKUP_GET_TASK_COMMENTS) which at runtime will ingest ClickUp task/comment body text authored by other users into the agent’s LLM context, creating an indirect prompt-injection path via outsider-authored free text.

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

• Potentially malicious external URL detected (high risk: 0.85). The skill requires adding and using the MCP endpoint https://rube.app/mcp at runtime (see RUBE_SEARCH_TOOLS requirement) which supplies tool schemas that directly control the agent's available tools and behavior, creating a remote control dependency.