Your question is Audit Authorization Boundaries for Agents. Take a moment with it on the right.
Talk me through your thinking if you like. When you're confident, submit your answer and I'll grade it like a real screen (7/10 or better passes).
How do you audit authorization boundaries in systems that utilize automated decision-making agents at Amazon? Explain how you would map trust boundaries, verify agent and tool permissions, detect confused-deputy and privilege-escalation paths, and produce evidence that authorization decisions are enforced. Address both design-time review and runtime validation, including failure handling and incident response.