Validating AI input | AWS Certified AI Practitioner (AIF-C01) original practice question

5.2Standard

A public chat receives huge or unsafe inputs.

Reduce cost and attack surface.

Choose two controls.

Hint 1: Focus on the requirement

Identify what must change and what must remain unchanged. Then choose the command whose scope matches that requirement.

Hint 2: Check each command's role

Separate commands that display information, change state, remove data, or affect a child process.

長さ・形式・文字コード・ファイル種別・レート・危険な指示を検査する: Oversized and some attack inputs are reduced.
超過・不正・不確実な入力へ明確なエラー、上限、隔離、人手確認を返す: A safe alternate path exists.
入力を無制限に受け付け、モデルへ全て渡す: Cost and attack surface grow.
入力検査で拒否した内容を全てログへ平文保存する: Sensitive data remains.

Detailed explanation

CorrectInspect length, format, encoding, file type, rate, and dangerous instructions

Oversized and some attack inputs are reduced.

CorrectReturn bounded errors, limits, quarantine, or human review and minimize rejection logs

A safe alternate path exists.

IncorrectAccept unlimited input and send everything to the model

Cost and attack surface grow.

IncorrectStore rejected input in plaintext without limits

Sensitive data remains.

An example you can run in a temporary verification environment.

AWS公式AIF-C01 Domain 5.2・2.3の入力検証、インジェクション、レート制限を確認する。

入力を無条件にモデルへ渡さず、拒否・隔離・ログ保護を設計できる。

Foundation review

Check whether the command acts on the current shell, a new process, an existing process, or a file.

Use the supplied command and compare the output with the expected result.

Question IDAWS-AIF-503

EnvironmentAWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認

Last technical review2026-08-20