senpi-trader-research

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

• Third-party content exposure detected (low risk: 0.10). In scripts/research.py, the required FIND/VET workflow calls discovery_* MCP tools (e.g., discovery_get_top_traders, discovery_get_trader_state, leaderboard_get_trader) which return JSON containing outsider-authored free-text fields only if the provider includes them; however the workflow never explicitly selects or directly ingests arbitrary user-submitted free text (it operates on structured trader/state data, and its inputs are only a trader address from the user).