Skip to content
AI Security

Interview question · Agent, Tool & MCP Security

How do AGENTS.md, rules files and editor or MCP config in a repository become an attack path against coding agents?

Repository instructions can influence a model; configuration can change execution. Trace creation, replacement and startup before deciding where approval must hold.

hardNewUpdated Nov 2026

Repository instructions can influence a model; configuration can change execution. Trace creation, replacement and startup before deciding where approval must hold.

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

An agent reviews an untrusted pull request in a disposable workspace. It can edit code and run tests; the team intends all new process-launch permissions to require separate approval.

  1. What if the sensitive configuration file does not exist yet?
  2. What if the shell can replace a file that the editor tool refuses to modify?
  3. What if a review dialog appears after the configured process has started?
  4. What release check would you require?

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 does the same-origin policy protect when an AI agent acts across logged-in sites?Next in this trackYour company runs hundreds of AI agents built by different teams. How do you govern the fleet?Next in this trackWhat can an agent gateway or MCP gateway enforce between agents and their tools, and what can it never see?
DISCUSSION · 0

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