Get Your CertAI-300PlayCompete
‹ All AI-300 questions

AI-300 Practice Question 69: Prompt Shields Indirect Attack

Microsoft Machine Learning Operations Engineer Associate (AI-300) · Test 7 · question 9 of 10

Implement generative AI quality assurance and observabilitymedium

A RAG assistant summarizes emails and web pages. An attacker hides text in a retrieved document that tells the model to ignore its system prompt and reveal confidential data. Which content safety capability is designed to detect this kind of attack?

Select one answer
Show answer and explanation

Answer:

  • D. Prompt Shields, with document (indirect attack) detection turned on

Prompt Shields detects two kinds of adversarial input: user prompt attacks (jailbreaks) and document attacks, also called indirect attacks, where malicious instructions are embedded in content the model is asked to process. The document detection targets the scenario in the question (option D).

- A is wrong because this feature flags known copyrighted text such as lyrics or articles. It does not look for instructions hidden in documents. - B is wrong because these thresholds score harmful language. A hidden instruction can be written in perfectly polite words. - C is wrong because attackers can rephrase the instruction endlessly, so an exact-match list cannot reliably detect it.

Reference: Prompt Shields in Microsoft Foundry

Practice Test 7 ›

Study guides for AI-300

AI-200 exam guide: Azure AI Cloud Developer AssociateAI-200 replaced AZ-204: what the Azure AI Cloud Developer exam tests, how it differs from AI-103, price in USD and INR, format and how to prepare.
How AI Is Changing Software Jobs: Where to PrepareHow AI is changing software jobs: what history shows, the evidence on junior developers, what Klarna learned, new AI roles and five domains to prepare for.
Best MLOps certifications 2026: which test real MLOpsThe best MLOps certifications in 2026 from Microsoft, Databricks, Google and AWS, ranked by how much each exam tests MLOps, with cost and order.
Best AI certifications 2026: AWS, Google, Microsoft, ClaudeThe best AI certifications in 2026 from AWS, Google, Microsoft, Claude and Databricks, by level, with price, status and which one to take first.
Microsoft AI certification path 2026: which exam firstMicrosoft AI certification path for 2026 - AI-901, AB-730, AI-103, AI-200, AI-300, AB-100, AI-500 and GH-300 by role, and which exam to take first.
What Is RAG? How Retrieval-Augmented Generation WorksWhat RAG is and how it works: chunking, embeddings, vector search, hybrid search, reranking, GraphRAG and agentic RAG on AWS, Google and Azure.