domain-research

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests public third‑party content — e.g., WHOIS/RDAP lookups from "https://mcp.domaindetails.com/lookup/{domain}", marketplace results from "https://api.domaindetails.com/api/marketplace/search?domain={domain}", Wayback Machine pages (web.archive.org), and other public APIs — and the agent is expected to read and interpret that untrusted, user/third‑party content as part of its workflow.