Skip to content
AI Security

Interview question · Agent, Tool & MCP Security

When should an agent act automatically, ask for approval or refuse?

Define automatic work within an existing grant, decisions that need new authority and prohibited effects. Assess data disclosure, impact, recovery and uncertain inputs without turning every step into another confirmation.

mediumNewUpdated Nov 2026

Define automatic work within an existing grant, decisions that need new authority and prohibited effects. Assess data disclosure, impact, recovery and uncertain inputs without turning every step into another confirmation.

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 4 follow-ups like an interviewer would

Alder has a recorded grant to send one approved report to Aria before 17:00. The assistant pauses and later resumes the task.

  1. Does resuming automatically require another confirmation?
  2. What if the agent proposes sending the report to Birch instead?
  3. What if the report depends on an externally authored document?
  4. What should an autonomy policy demonstrate?

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 trackHow do you stop injected instructions from persisting through agent memory or long-term state?Next in this trackA prompt injection caused an unauthorized tool call in production. Walk through containment and the fix.Next in this trackSecure a coding agent that can run shell commands on a developer machine or in CI.
DISCUSSION · 0

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