smart-money-tracker

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

• Third-party content exposure detected (high risk: 0.90). The skill's required runtime workflow (Step 2 "Fetch Smart Money Data" and the "Safety Checks" sections) explicitly calls external MCPs—OnchainOS commands like dex-market signal-list, dex-token info, dex-token price-info and third-party services (GoPlus, Rug Munch, Nansen)—to ingest public on-chain signals, token metadata and social links (untrusted/user-generated) which the agent must read and use to make recommendation/block decisions and generate copy-plans.