clickup-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 reads user-generated ClickUp content via required toolkit calls (e.g., CLICKUP_GET_TASK, CLICKUP_GET_TASK_COMMENTS, CLICKUP_GET_TASKS) so third-party task descriptions and comments can be ingested and influence subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires connecting at runtime to the MCP server https://rube.app/mcp (via RUBE_SEARCH_TOOLS) to fetch current tool schemas that directly influence agent actions/prompts and is presented as a required dependency.