group-benchmarking

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

• Third-party content exposure detected (high risk: 0.70). The skill's workflow (Steps 1–3) explicitly instructs the agent to spawn the marketcheck-cowork-plugin (lot-scanner and lot-pricer) and call mcp__marketcheck__get_sold_summary to fetch inventory/market data (including "Mode: full (with DOM stats)"), meaning it ingests external public listing/market content that the agent reads and uses to drive pricing, rankings, and actions.