A prompt includes user text and fixed safety rules.
User text must not override the rules.
Choose two controls.
Keep trusted system and application constraints separate from untrusted content, authorize tools independently, and validate output before use.
Detailed explanation
User text cannot redefine the application policy.
User text cannot redefine the application policy.
Prompt instructions are not an access-control boundary.
Prompt instructions are not an access-control boundary.
Untrusted content can cause instruction injection.
Untrusted content can cause instruction injection.
Documents can contain malicious or irrelevant instructions.
Documents can contain malicious or irrelevant instructions.
Try it yourself
An example you can run in a temporary verification environment.
AWS公式AIF-C01 Domain 2.3のプロンプトインジェクション、Guardrails、認可を確認する。Expected result
プロンプトの優先順位と、アプリ・IAM側の強制制御を分離できる。Key points
- Trusted instruction
- Untrusted input
- Validation
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.