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 explicitly fetches token metadata, descriptions and social links from public endpoints (e.g., https://web3.binance.com token metadata/search APIs with "links"/"previewLink"/"description") and k-line data from https://dquery.sintral.io, and SKILL.md directs using that metadata and social links for "Project Research" and analysis—clearly exposing the agent to untrusted, user-generated third‑party content that could influence its decisions or actions.