Retrieved documents are passed to a model.
Malicious instructions inside a document must not execute.
Choose two controls.
Mark retrieved text as untrusted evidence separate from system constraints, validate output, and authorize tools independently.
Detailed explanation
Document text cannot redefine policy.
Document text cannot redefine policy.
Model interpretation is not access control.
Model interpretation is not access control.
External data can override constraints.
External data can override constraints.
Retrieval does not grant trust or permission.
Retrieval does not grant trust or permission.
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対策を確認する。Expected result
検索文書の内容とアプリケーション命令・認可を分離できる。Key points
- Document injection
- Trust boundary
- Authorization
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.