design-agentic-infrastructure

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

• Third-party content exposure detected (low risk: 0.10). The required runtime workflow is a design-time consultancy (steps 1–4) that does not ingest outsider-authored free text; the only “free text” it handles is the user’s own brief inputs, and step 5 is a web search for tool/pricing pages (not outsider-submitted queue/feed content feeding the agent without selecting specific sources).