Skip to content
AI Security

Interview question · LLM Application Security

What is unbounded consumption, or denial of wallet, and how do you prevent it?

An easy question with a revealing follow-up. The answer that scores limits cost at every layer, including the agent loop, not just requests per minute.

easyNewPreparation tags: OpenAI, Anthropic, AmazonUpdated Nov 2026

An easy question with a revealing follow-up. The answer that scores limits cost at every layer, including the agent loop, not just requests per minute.

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 6 follow-ups like an interviewer would

An attacker sends long, expensive prompts to a free AI feature and runs up a large bill over a weekend.

  1. Why is this different from a classic DoS?
  2. What controls limit cost per user?
  3. What if attackers use many accounts?
  4. What if the free feature is being used as a free model proxy by another service?
  5. What should happen when spend spikes over a weekend?
  6. What would you put in place?

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
Next in this trackA customer says your chatbot showed them another user's data. What do you check first?Next in this trackCan embeddings leak information about their source text? What does that mean for how you store them?Next in this trackHow should prompts, traces and logs in an LLM application handle personal data and secrets?
DISCUSSION · 0

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