Skip to content
AI Security

Interview question · Agent, Tool & MCP Security

Design and test an agent’s file-write boundary, including symlinks and concurrent changes.

Separate task authorization, path resolution and safe publication. A resolved path is only a snapshot; test concurrent changes, protected targets and aggregate limits without treating a few passing cases as proof.

hardNewUpdated Nov 2026

Separate task authorization, path resolution and safe publication. A resolved path is only a snapshot; test concurrent changes, protected targets and aggregate limits without treating a few passing cases as proof.

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

Alder’s editor validates a release-note path, then opens it later. Another worker can change directories and edit the same file during that interval.

  1. Does the earlier resolved path guarantee the later write stays inside the workspace?
  2. May the tool overwrite a newer version if the target is authorized?
  3. Do passing offline validator tests establish filesystem containment?
  4. What should the implementation review deliver?

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 trackAn AI agent caused financial damage in production. What do you do in the first hour?Next in this trackYour security operations agent reads logs, alerts and tickets. How do you stop attacker-controlled text in them from steering it?Next in this trackHow do you test a function-calling agent for unintended tool use, and what number do you report?
DISCUSSION · 0

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