mev-bot-infrastructure-analysis-agent

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly requires ingesting and interpreting public third‑party sources (e.g., "Toolchain and data sources" and the operational workflow references Jito explorers, EVM builder dashboards, Dune MEV tables, public mempool archives and APIs) as part of its analysis, so untrusted web content could influence agent decisions.