flash-loan-exploit-investigator-agent

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly requires ingesting and anchoring analysis on public tx hashes or "public write-up link" and lists explorer/indexer/Dune/Flipside sources in "Toolchain and data sources" and "Operational workflow (suggested) → Intake", so it will consume untrusted public/web content (explorers, write-ups, analytics) that can influence analysis and tool use.