audience-segmentation-brief

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow includes a mandatory web search step (“Web search (Claude — MANDATORY): Search Kantar Worldpanel…”) which fetches public web content and injects its scraped page text into the agent’s LLM context, creating an indirect prompt-injection risk from outsider-authored material.