claims-valuation

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly calls marketcheck APIs in Step 3 (mcp__marketcheck__search_active_cars and mcp__marketcheck__search_past_90_days) to pull public retail listings and sold transactions—untrusted third‑party listing data that the agent ingests and uses to determine FMV and settlement decisions, so external content can materially influence actions.