consulting-analysis

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly expects and ingests External Search Findings and a Data Summary (Phase 1→2 Handoff and Phase 2 Inputs) and its Data Requirements list "Suggested Sources" including social media, e‑commerce platforms, news and industry reports, and the Phase 2 workflow (Steps 2.1–2.4) requires the agent to read and act on those external URLs/summaries to generate charts and narrative, which exposes it to untrusted third‑party content that could alter behavior.