Skip to content
AI Security

Interview question · Agent, Tool & MCP Security

An agent needs to answer questions from a database. How do you design and secure its SQL tool?

Choose fixed query tools or bounded exploratory SQL, then verify the database role, tenant context, views, callable functions and resource controls. Read-only and row limits alone do not protect confidentiality or cost.

mediumNewUpdated Nov 2026

Choose fixed query tools or bounded exploratory SQL, then verify the database role, tenant context, views, callable functions and resource controls. Read-only and row limits alone do not protect confidentiality or cost.

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 analytics agent runs SELECT queries through a pooled connection. The team enables row security and caps the returned output at 100 rows.

  1. Do those settings prove that each tenant sees only its own data?
  2. What if the connection previously served another tenant?
  3. Can a 100-row output cap prevent an expensive aggregate?
  4. What evidence should the database review 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 trackA long-running agent works on a task for hours. When must it stop and re-confirm with the user, and how do you bound it in the meantime?Next in this trackCan the same model that proposes an agent's action also approve it, or act as its guardrail? What should decide instead?Next in this trackWhat evidence supports a claim that a compromised agent cannot retrieve production secrets?
DISCUSSION · 0

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