Skip to content

Interview question · Prompt Injection & Jailbreaks

How has the move from chatbots to agents changed the impact of prompt injection?

Compare actual sources, identities, audiences, effects and persistence. Review what tools add without dismissing text-only harms or assuming user-scoped credentials authorize every task.

mediumNewUpdated Nov 2026

Compare actual sources, identities, audiences, effects and persistence. Review what tools add without dismissing text-only harms or assuming user-scoped credentials authorize every task.

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.

signing in unlocks more free answers per topic

What if · the follow-ups in this answer

The answer works through 4 follow-ups like an interviewer would

A fictional support team is adding scheduling, ticket updates and memory to an assistant that already reads private account records. Customers control submitted messages but cannot expand account, audience or operation grants.

  1. The existing chatbot has private records but no tools. Does that establish low impact?
  2. The agent acts only with the victim user's permissions. Can it still be a confused deputy?
  3. A hostile memory entry is proposed but rejected by storage policy. Has persistent compromise occurred?
  4. What must change in the release evidence?

Each rung has a nudge, a model answer, the principle that carries over and the weak answer to avoid. Sign in free to open it.

UP NEXT ON YOUR JOURNEY
DISCUSSION · 0

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