Users enter free-form text into an AI application.
Reject excessive, prohibited, or malicious content before generation.
Choose two appropriate controls.
Validate length, format, data classification, and harmful content, then route rejected input to safe handling.
Detailed explanation
Unexpected input and cost or leakage risk are reduced.
Unexpected input and cost or leakage risk are reduced.
The application can branch before the model sees the input.
The application can branch before the model sees the input.
Injection and privilege escalation are possible.
Injection and privilege escalation are possible.
The policy is bypassed and the failure is hidden.
The policy is bypassed and the failure is hidden.
Try it yourself
An example you can run in a temporary verification environment.
AWS公式生成AIセキュリティ・GuardrailsとAIF-C01 Domain 2.3を確認する。Expected result
入力検証をコスト、安全性、権限の境界として設計できる。Key points
- Input validation
- Data class
- Reject
Notes
- Environment: AWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
- Command output formatting can vary slightly by distribution or tool version.
- Run the example in a temporary directory or process when possible.
Foundation review
Read the scope first
Check whether the command acts on the current shell, a new process, an existing process, or a file.
Verify the observable result
Use the supplied command and compare the output with the expected result.