Conversation history contains an instruction to ignore previous rules.
Limit tool actions.
Choose two controls.
Reapply fixed policy at every turn, separate history and retrieved text by trust, and restrict tools with allowlists, argument validation, and approval.
Detailed explanation
Old text cannot easily override policy.
Old text cannot easily override policy.
Generated text has limited authority.
Generated text has limited authority.
Untrusted content can persist.
Untrusted content can persist.
Attacks or mistakes can run.
Attacks or mistakes can run.
Try it yourself
An example you can run in a temporary verification environment.
AWS公式AIF-C01 Domain 2.3・5.2のプロンプトインジェクション、ツール利用、入力検証を確認する。Expected result
会話履歴とツール引数を不信なデータとして扱い、権限を限定できる。Key points
- Multi-turn
- Allowlist
- Argument 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.