query-token-info

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

• Third-party content exposure detected (high risk: 0.80). The skill calls public Binance web3 and third-party APIs (e.g., the Token Search and Token Metadata endpoints at https://web3.binance.com/... and previewLink/links fields shown in API 1 & 2) and ingests token descriptions and external social/website links (user-provided content) as part of its required workflow, which the agent is expected to read and which could materially influence analysis or actions.