Skip to content
AI Security

Interview question · Prompt Injection & Jailbreaks

How do attackers steal what is in an LLM application's context: system prompts, retrieved documents, other users' data and tool results?

Map protected context to its actual readers. Distinguish unauthorized retrieval from redistribution, inspect drafts and rendering, and verify disclosure without assuming every prompt inevitably leaks.

mediumEssentialNewUpdated Nov 2026

Map protected context to its actual readers. Distinguish unauthorized retrieval from redistribution, inspect drafts and rendering, and verify disclosure without assuming every prompt inevitably leaks.

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 4 follow-ups like an interviewer would

Imani may read internal negotiation notes for a staff briefing. Suppliers may receive an approved response, but not internal price limits; shared drafts have their own readers.

  1. What if Imani names the supplier as the reply recipient?
  2. What if a URL contains the synthetic marker but no request receipt exists?
  3. What if the draft is never sent but a supplier collaborator can read it?
  4. What would your confidentiality review hand off?

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 trackWhy can a model follow lower-priority instructions, and how do you investigate it?Popular right nowWhat security risks does the Model Context Protocol (MCP) introduce?Popular right nowExplain the lethal trifecta and use it to triage an agent design in two minutes.
DISCUSSION · 0

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