Skip to content
AI Security

Interview question · LLM Application Security

Your RAG system is returning the wrong documents. What security causes would you check?

Most bad retrieval is a quality bug; some of it is an attack or an access failure. The scored answer separates the cases quickly and checks the security ones first.

mediumNewPreparation tags: Microsoft, Google, DatabricksUpdated Nov 2026

Most bad retrieval is a quality bug; some of it is an attack or an access failure. The scored answer separates the cases quickly and checks the security ones first.

Make your first attempt

What would you say before reading the answer?

  1. 01 State the assumptions your answer depends on.
  2. 02 Explain the mechanism and choose a control.
  3. 03 Name a condition that would change your decision.

The worked answer includes an approach, scoring criteria and follow-up questions. Compare the reasoning with your own.

10 answers per topic instead of 5, plus saved progress and bookmarks · costs nothingor unlock all 529 remaining answers · $25

Every worked answer in all 17 topics, every lesson in every course, the full concept curriculum, the complete practice-test bank, and the downloadable security field guides.

6 months · One payment · No auto-renewal

What if · the follow-ups in this answer

The answer works through 6 follow-ups like an interviewer would

A RAG assistant keeps citing an unrelated vendor policy document for many different questions.

  1. What could cause one document to appear everywhere?
  2. How would you tell a quality problem from poisoning?
  3. What if the document contains instructions to the model?
  4. How do you improve retrieval in general?
  5. What monitoring would catch this earlier?
  6. What would you put in place?

Each rung has a nudge, a model answer, the principle that carries over and the weak answer to avoid. Premium opens every answer and ladder.

UP NEXT ON YOUR JOURNEY
Next in this trackYour assistant's answers about one product changed overnight. Was the index poisoned or a source edited?Next in this trackDesign abuse policy, reporting and enforcement for a consumer generative AI feature.Next in this trackYour product team is adding an AI assistant to an existing SaaS product. What changes in the threat model?
DISCUSSION · 0

No comments yet. Share a correction or a different way to answer it.