token-research

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md workflow (Steps 2–5) explicitly calls defillama:get_token_prices, defillama:get_token_unlocks, defillama:get_token_tvl and defillama:get_yield_pools to ingest public DeFiLlama data, so the agent reads third-party web-sourced content that can materially influence its analysis and actions.