Skip to content
AI Security

Interview question · Agent, Tool & MCP Security

An agent keeps shared memory across users. How do you stop one user, or a slow campaign, from poisoning it?

Treat a wider memory audience as a publication decision. Check the publisher, evidence, disclosure scope and version separately; repeated copies, familiar account names and a verified label do not establish all four.

hardNewUpdated Nov 2026

Treat a wider memory audience as a publication decision. Check the publisher, evidence, disclosure scope and version separately; repeated copies, familiar account names and a verified label do not establish all four.

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

Aria’s support assistant proposes turning ticket summaries into shared knowledge. Several users submit the same workaround, while one summary also contains a private customer exception.

  1. What if the same workaround appears in five summaries?
  2. What if the customer exception is true?
  3. What if rollback restores a version from before a deletion request?
  4. How would you test the promotion workflow?

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 should an agent be allowed to remember, for how long, and how do you delete memories, including the embeddings derived from them?Next in this trackDesign trust between AI agents owned by different organisations, such as your procurement agent and a supplier's sales agent.Next in this trackHow would you measure an agent's excessive-agency risk quantitatively, so you can compare designs and track it over time?
DISCUSSION · 0

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