dealer-intelligence-brief

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

• Third-party content exposure detected (high risk: 0.80). The skill's workflow (steps 1–5 in SKILL.md) directly calls MarketCheck endpoints (mcp__marketcheck__search_active_cars, mcp__marketcheck__predict_price_with_comparables, and mcp__marketcheck__get_sold_summary) to ingest public dealer inventory and sold-listing data—including searches by dealer name or domain—which the agent reads and uses to compute LTVs and recommend products, exposing it to untrusted third-party content that could enable indirect prompt injection.