dom-monitor

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly calls third‑party Marketcheck APIs (mcp__marketcheck__get_sold_summary and mcp__marketcheck__search_active_cars) in multiple workflow steps to ingest public marketplace/listing data (sold and active inventory) and uses those untrusted, user‑sourced metrics to drive signals and automated decisioning, so external content can materially influence the agent's actions.