Skip to content
AI Security

Interview question · LLM Application Security

Write a sanitiser that keeps links and images in streamed model Markdown inert until they are validated.

Rendering is an outbound channel. The scored answer removes images, rewrites unapproved links, strips raw HTML, and only releases streamed text once it can no longer turn into something dangerous.

hardNewPreparation tags: Microsoft, Google, OpenAIUpdated Nov 2026

Rendering is an outbound channel. The scored answer removes images, rewrites unapproved links, strips raw HTML, and only releases streamed text once it can no longer turn into something dangerous.

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 chat app renders model output as Markdown while it streams, to make responses feel fast.

  1. What if the output includes an image link with data in the URL?
  2. What if you sanitise each chunk separately?
  3. What if links are clickable to any domain?
  4. What if the model output includes raw HTML?
  5. What backstop works even if the sanitiser has a bug?
  6. What rendering policy would you use?

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 trackCan a vector search API leak confidential information even when it never returns the documents themselves?Next in this trackCosine similarity decides what a RAG system retrieves. How would you make retrieval prefer trustworthy sources instead of just similar ones?Next in this trackDesign an ingestion pipeline for a RAG index that resists poisoning, and explain how you would estimate the poisoning risk that remains.
DISCUSSION · 0

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