defi-data-fetcher

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow and source-priority docs (SKILL.md and references/source-priority.md) explicitly require fetching and ingesting live data from open public third-party sources such as protocol APIs/subgraphs, DeFiLlama, and public Dune queries, which the agent reads and reconciles to produce metrics and confidence—so untrusted content can materially influence actions.