Exam AI-103 Topic 1 Question 134 Discussion
Actual exam question for Microsoft's AI-103 exam
Question #: 134
Topic #: 1
Question #: 134
Topic #: 1
You have an app named App1 that uses a Microsoft Foundry multimodal model deployment.
App1 runs optical character recognition (OCR) on uploaded images and appends the OCR output to the prompt as additional context.
Some uploaded images contain embedded text.
You need to prevent potentially malicious instructions from being processed by the model.
What should you use?
App1 runs optical character recognition (OCR) on uploaded images and appends the OCR output to the prompt as additional context.
Some uploaded images contain embedded text.
You need to prevent potentially malicious instructions from being processed by the model.
What should you use?
Suggested Answer: D Vote an answer
The correct answer is D. prompt shields for documents . The OCR text is extracted from uploaded images and appended as additional context, so it is third-party content rather than a direct trusted user instruction.
Microsoft Foundry Prompt Shields distinguish between user prompt attacks , which are malicious instructions directly supplied as user prompts, and document attacks , which are hidden or embedded instructions in third-party content such as documents, emails, webpages, or grounded data. Microsoft also notes that Prompt Shields analyze indirect attacks embedded in input documents or images.
This scenario is an indirect prompt injection pattern: an uploaded screenshot may contain text that says to ignore the system prompt or perform unauthorized actions. Because the OCR output is being passed to the multimodal model as contextual content, the appropriate protection is Prompt Shields for documents, which scans externally sourced context for malicious embedded instructions before generation. Protected material text detects known copyrighted text in model outputs, not prompt injection. Image moderation detects harmful visual content categories, not malicious instructions in extracted context. Prompt Shields for user prompts are less precise here because the risk comes from document-like content derived from the uploaded image.
Reference topics: Prompt Shields, document attacks, indirect prompt injection, multimodal safety, OCR- derived context, and Foundry guardrails.
Microsoft Foundry Prompt Shields distinguish between user prompt attacks , which are malicious instructions directly supplied as user prompts, and document attacks , which are hidden or embedded instructions in third-party content such as documents, emails, webpages, or grounded data. Microsoft also notes that Prompt Shields analyze indirect attacks embedded in input documents or images.
This scenario is an indirect prompt injection pattern: an uploaded screenshot may contain text that says to ignore the system prompt or perform unauthorized actions. Because the OCR output is being passed to the multimodal model as contextual content, the appropriate protection is Prompt Shields for documents, which scans externally sourced context for malicious embedded instructions before generation. Protected material text detects known copyrighted text in model outputs, not prompt injection. Image moderation detects harmful visual content categories, not malicious instructions in extracted context. Prompt Shields for user prompts are less precise here because the risk comes from document-like content derived from the uploaded image.
Reference topics: Prompt Shields, document attacks, indirect prompt injection, multimodal safety, OCR- derived context, and Foundry guardrails.
by Harold at Jul 28, 2026, 01:23 PM
0
0
0
10
Comments
Upvoting a comment with a selected answer will also increase the vote count towards that answer by one. So if you see a comment that you already agree with, you can upvote it instead of posting a new comment.
Report Comment
Commenting
You can sign-up / login (it's free).