clickup-integration-agent

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 ingests user-generated ClickUp content (e.g., get_tasks, get_task_comments, get_document/get_document_pages in the "Phase 1: Discovery & Data Collection" and "Monitoring" sections of SKILL.md) and uses that data for analysis and to drive actions (create/update/move tasks), so untrusted third-party content from ClickUp workspaces could indirectly inject instructions affecting agent behavior.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill invokes "npx -y @taazkareem/clickup-mcp-server@latest" at runtime (the package/repo: https://github.com/taazkareem/clickup-mcp-server), which fetches and executes remote code as a required MCP server dependency.