onchain

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and parses public, user-generated prediction-market content (Polymarket) and other open APIs/block explorers (Etherscan/Solscan, CoinGecko) as part of its runtime workflow and the SKILL.md "polymarket" commands and "Agent Integration" sections instruct agents to interpret that data and act on it, so untrusted third‑party content can influence agent decisions.