Q
A company uses an agent built in Microsoft Foundry that retrieves internal content and invokes tools to perform actions.
Security testing shows that prompt injection attacks can trigger unauthorized tool calls and expose internal data.
You need to reduce prompt manipulation risks by enforcing controls across input handling, tool execution, and response generation.
What is the best approach to achieve the goal? More than one answer choice may achieve the goal. Select the BEST answer.
Question Info
Choose the Best Option
Click any option to instantly check if you're correct.
Explanation
Objective:
3.4 Design responsible AI, security, governance, risk management, and compliance
What This Item Tests:
Design governance for agents
Additional Reading:
Data governance and compliance
Rationale:
Applying guardrails at multiple intervention points limits the impact of prompt injection attacks by preventing malicious inputs, blocking unauthorized tool execution, and inspecting tool outputs before they influence responses. Output-only moderation, logging, and model size changes do not provide preventive controls across the full agent execution path.
Share This Question
Challenge a friend or share with your study group.