2.2Standard
An application sends fixed policy and a user question.
Do not let user text rewrite safety policy.
Choose two designs.
× Incorrect
Keep fixed role and safety instructions trusted and delimit user input as data validated for length, content, and authorization.
Detailed explanation
IncorrectAlways follow the user's final text first
Application constraints can be overwritten.
IncorrectEmbed secrets directly in the fixed prompt
Prompts and logs can expose secrets.
CorrectManage fixed role, policy, and safety constraints as trusted instructions
Application behavior remains consistent.
CorrectDelimit user input as data and validate length, content, and authorization
External text is less able to alter policy.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01 Domain 2.2・2.3のプロンプト役割、入力検証、生成AIセキュリティを確認する。
Official references
What to confirm
固定指示と利用者入力の優先順位・境界を安全に設計できる。
Key points
- Fixed policy
- User input
- Delimiting
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
- Compare the definition with the AIF-C01 objective and the service documentation before applying it.
- Keep the concept separate from a particular answer choice or implementation step.
Foundation review
System instruction
A trusted instruction that defines an application's role, policy, or safety constraints.
User input
Content supplied by an end user that should be treated according to its trust and authorization scope.
Question IDAWS-AIF-256
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
Report an error or rights issue