security-audit

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

• Third-party content exposure detected (high risk: 0.90). The skill's fetch_contract.py script (and README/SKILL.md "Get contract source" workflow) explicitly fetches verified source code from public blockchain explorers like Etherscan/Solscan, meaning the agent ingests untrusted, user‑provided third‑party content which directly drives static analysis, PoC generation and follow‑on actions.