AI-103 Question Preview

Safe Public Question Preview 3

Only the demo-safe public version is shown here. Correct answers, full explanations, internal IDs, and paid-only content stay protected.

Multi SelectImplement generative AI and agentic solutions
Question 3. You have a Microsoft Foundry project that contains an agent. The agent accepts user-uploaded screenshots and uses a multimodal chat model. Some screenshots contain potentially malicious embedded text. You need to prevent a prompt injection attack and ensure that third-party content is treated as lower trust. How should you configure prompt shields for document attacks? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point. Answer:
A. Disable the shield.
B. Set action to block.
C. Set action to annotate.
D. Enable Spotlighting.
E. Create a custom blocklist.
F. Use optical character recognition (OCR) to extract the text from the images first.
Explanation is locked. Start the demo or unlock full access to review explanations inside the protected test engine.
Open safe question previewReport Question
Start Interactive DemoBuy Full Access

Related Safe Previews

Question 1Question 2Question 4Question 5All Preview Questions

FAQ

Does this page show the answer?

No. Answers and explanations are protected inside the private test engine.