lending-fit-analyzer

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches dealer inventory and listing details from MarketCheck (calls like mcp__marketcheck__search_active_cars and mcp__marketcheck__predict_price_with_comparables in the SKILL.md workflow), which are public third‑party listings/user‑generated content that the agent reads and uses to drive LTV calculations and lending decisions, so untrusted content could materially influence actions.