Your question is Design Security for Agentic Applications. 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).
You are building an agentic application that can retrieve documents, call tools, and take actions on a user's behalf. The system must handle untrusted inputs from users, retrieved content, and external tools, while keeping the assistant useful.
What are the primary security vectors for agentic applications, and how do you mitigate them using tools like NeMo Guardrails?
