solana-defi-vulnerability-analyst-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 obtaining and interpreting public third‑party content (e.g., "Obtain verified source from explorers or repos", using "Dune/Flipside‑style decoded tables", and linking to "explorer txs" and instruction traces), so the agent will ingest untrusted public web/user‑generated data that can influence its analysis and decisions.