2.3Standard
The prompt contains application rules, user input, and retrieved documents.
External text must not override the rules.
Choose two practices.
× Incorrect
Separate trusted system and application constraints from untrusted text, treat documents as data, and validate output and tool arguments.
Detailed explanation
IncorrectLet user text redefine fixed rules
Untrusted input overrides policy.
IncorrectExecute instructions found in retrieved documents
Data gains unintended authority.
CorrectClearly separate fixed system and application constraints from user and retrieved text
Trusted and untrusted instructions differ.
CorrectTreat external text as data and validate output before tools or display
Injection impact is reduced.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01 Domain 2.3のプロンプトインジェクション、信頼境界、出力検証を確認する。
Official references
What to confirm
システム制約・利用者入力・検索文書の信頼度を分離できる。
Key points
- Trust boundary
- Instruction separation
- 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
- 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
Trust boundary
A separation between content or identities with different levels of authority and trust.
Prompt injection
An attempt to alter model behavior by placing instructions in untrusted content.
Question IDAWS-AIF-397
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