A chatbot filters user prompts but also consumes partner webpages and sends generated output to users. Which design best follows layered AI content controls?

Choose the single best answer.

A.Give the model more data permissions to reduce false positives
B.Validate external content and outputs as well as prompts while retaining independent authorization
C.Trust partner webpages automatically because they are not typed by users
D.Remove output checks because prompt filtering has already run

Show the answer and explanation

✓ Correct answer

Validate external content and outputs as well as prompts while retaining independent authorization

Validate external content and outputs as well as prompts while retaining independent authorization: Multiple entry and output paths need safeguards; filtering still does not replace permissions. Trust partner webpages automatically because they are not typed by users: External content can carry indirect prompt injection. Remove output checks because prompt filtering has already run: A filtered input does not guarantee safe output. Give the model more data permissions to reduce false positives: Increasing privileges expands exposure rather than adding content controls.

Read the source reference

Read and review here, or open the app to practise and save your results on this device.

Practise in the app

Unofficial study material. Not affiliated with or endorsed by Microsoft. These are original learning questions, not actual exam questions. Product capabilities and exam objectives can change; verify current Microsoft documentation. Practice scores do not predict or guarantee an exam result.