Skip to content
AI Security

Interview question · Prompt Injection & Jailbreaks

Design an email assistant that bounds the harm from prompt injection.

Design around actual read, draft, preview and send audiences. Bind current grants and approvals to the operation, handle queued changes and evaluate the content risks that remain.

expertNewUpdated Nov 2026

Design around actual read, draft, preview and send audiences. Bind current grants and approvals to the operation, handle queued changes and evaluate the content risks that remain.

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

Mina uses a fictional shared-mailbox assistant for selected-thread summaries, drafts and replies. External messages and restricted internal notes have different audiences, and rule administration is outside the first release.

  1. The assistant saves a staff-note summary as a draft in a shared mailbox. Is it private until sent?
  2. A recipient is already on the thread. May the reply include any note Mina can read?
  3. A send was approved, then the draft changes before the worker runs. What should execute?
  4. What would make the initial release defensible?

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 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?Next in this trackMap a multi-stage indirect prompt injection onto a kill chain. Where would you place detections and controls at each stage?
DISCUSSION · 0

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