mckinsey-consultant

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly performs web_search and ingests public third-party content as part of its workflow (see STEP 3 / STEP 6: "执行2-5次web_search" and "执行15-30次web_search", and the Excel data sheets that record source URLs such as 36kr, iResearch and arbitrary report URLs), so the agent will read and interpret untrusted open-web content that could carry indirect prompt injection.