AI-103 Implement Generative AI And Agentic Solutions Practice Question
You are implementing indirect prompt injection defenses in a RAG application where documents are ingested from public web pages. Which THREE mitigation strategies should you deploy? (Choose THREE)
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Use strict structural delimiters (like XML tags) to isolate retrieved context from system instructions
Prompt shields in Content Safety, strict prompt delimiters separating data from instructions, and content validation filters protect against indirect prompt injection.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Use strict structural delimiters (like XML tags) to isolate retrieved context from system instructions
Why this is correct
XML tags help the model distinguish untrusted retrieved data from trusted system instructions.
- ✗
Trust all incoming web page text unconditionally without inspection
Why it's wrong here
Trusting external text unconditionally exposes the agent to indirect prompt injection.
- ✗
Disable all content moderation filters to maximize processing speed
Why it's wrong here
Disabling filters removes security guardrails.
- ✓
Implement output validation filters to check model completions for unauthorized actions or exfiltration attempts
Why this is correct
Output validation catches any successful injection attempts before responses reach users.
- ✓
Enable Prompt Shields for indirect prompt injection in Azure AI Content Safety
Why this is correct
Prompt Shields detect malicious instructions hidden within retrieved web pages or documents.
About these practice questions
This AI-103 question is part of Courseiva's 510-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed August 2026 · checked against the official Microsoft exam blueprint
This AI-103 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-103 exam.