Skip to content
AI Security

Interview question · Prompt Injection & Jailbreaks

Trace how instructions can reach a model through emails, web pages and tool outputs in a real application.

Follow individual fields from their authors through tools, summaries and actual model exposure. Separate service-authoritative identifiers from quoted prose, then check each output and operation.

mediumNewUpdated Nov 2026

Follow individual fields from their authors through tools, summaries and actual model exposure. Separate service-authoritative identifiers from quoted prose, then check each output and operation.

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

Ellis summarizes customer ticket T-42 and suggests an internal owner. A trusted ticket service returns both customer prose and service-generated identity fields.

  1. What if the response is authenticated but its description is customer-written?
  2. What if the source appears in search results but is truncated from the request?
  3. What if a generated note is stored for later sessions?
  4. What should the field-to-effect record contain?

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 trackDesign an email assistant that bounds the harm from prompt injection.Next in this trackHow would you test whether a RAG assistant is vulnerable to indirect prompt injection, without harming production?Next in this trackWhat evidence should decide an AI assistant's residual-risk target?
DISCUSSION · 0

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