Skip to content
AI Security

Interview question · Agent, Tool & MCP Security

Your agent browses the web and reads the user's email. What is the worst a poisoned web page can do?

Trace which private data can reach which destinations when browsing and email share a task. Rank harms by the capabilities and checks actually present, and preserve useful combined workflows within a narrow grant.

hardNewUpdated Nov 2026

Trace which private data can reach which destinations when browsing and email share a task. Rank harms by the capabilities and checks actually present, and preserve useful combined workflows within a narrow grant.

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 asks Alder to compare one hotel confirmation email with public cancellation terms. The assistant can read the thread and fetch approved web resources.

  1. Does the absence of an email-send tool prove that the confirmation cannot leave?
  2. What if the public-site worker returns structured fields to the email worker?
  3. May the comparison task change mailbox forwarding settings?
  4. What should the evaluation retain?

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 trackWhat do you log about agent actions so you can audit them and respond to an incident?Next in this trackIn an agent, where may the model reason, and where must deterministic code own the decision?Next in this trackHow do rate limits, budgets and loop limits reduce abuse of an AI agent, and how do you set them?
DISCUSSION · 0

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