Skip to content
AI Security

Interview question · Prompt Injection & Jailbreaks

What are invisible-character tricks in prompt injection, and where should text be normalised?

Separate Unicode normalization, hidden controls, bidirectional display and confusable identifiers. Use a harmless offline example to choose field-specific checks without damaging legitimate language.

mediumNewUpdated Nov 2026

Separate Unicode normalization, hidden controls, bidirectional display and confusable identifiers. Use a harmless offline example to choose field-specific checks without damaging legitimate language.

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

Amara routes multilingual support tickets. The customer controls ticket prose; trusted service code supplies team identifiers and enforces assignment permission.

  1. What if a valid joiner remains after NFKC?
  2. What if two team labels look identical to the reviewer?
  3. What if cleanup fixes the suspicious ticket but breaks valid names?
  4. What would make the routing fix reviewable?

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 trackArchitect a prompt injection detection system for production and show how you would know it works.Next in this trackWhat is a canary token in an LLM application, and what can it detect?Next in this trackHow do prompt injections hidden in images, audio and documents work, and how would you test for them?
DISCUSSION · 0

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