Skip to content
AI Security

Interview question · Prompt Injection & Jailbreaks

Explain the dual LLM and plan-then-execute patterns, and what each one costs.

Compare controller-enforced workflows with mediated planner inputs. Trace opaque values, bounded fields, runtime branches and retries to the actual permission decision.

hardNewUpdated Nov 2026

Compare controller-enforced workflows with mediated planner inputs. Trace opaque values, bounded fields, runtime branches and retries to the actual permission decision.

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

Arun designs a fictional issue classifier and weekly digest. Contributors control issue text, while the application controls project access, permitted operations and the digest audience.

  1. The reader returns valid JSON with a long free-form summary. Can the planner safely read it just because the schema passed?
  2. The controller commits only to the tool names search and send. Are the recipient and record scope fixed?
  3. A retry includes the full source-derived exception in the planner prompt. Does the original isolation claim still hold?
  4. Which design would you propose for the digest?

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 do capability-based designs such as CaMeL bound what a prompt injection can do?Next in this trackTrace how instructions can reach a model through emails, web pages and tool outputs in a real application.Next in this trackDesign an email assistant that bounds the harm from prompt injection.
DISCUSSION · 0

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