defi-security-audit-agent

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly instructs the agent to fetch and interpret public third-party content—e.g., "Pull verified source from chain explorers" and analytics/explorer sources listed in the Toolchain (Etherscan family, Solscan, Dune, Flipside)—which are untrusted/user-generated public sources that the agent will read and use to drive its analysis and actions.