messari-deep-research

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

• Third-party content exposure detected (high risk: 0.70). The skill starts and polls Messari's external deep-research API (https://api.messari.io/ai/v1/deep-research), which explicitly crawls news, on-chain data, and public knowledge graphs and returns a report (result/sources) that the agent ingests and acts on, so untrusted third-party content can materially influence behavior.