consulting-analysis

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly requires ingesting External Search Findings and a Data Summary (including source URLs and summaries) provided by downstream data-collection skills (see "Phase 1→2 Handoff" and "Phase 2 Inputs" / Step 2.1), and those suggested sources include open/public sites (industry reports, news, social media, e-commerce), so the agent will read and act on untrusted third‑party content as part of its required workflow.