Only an internal application may call an inference endpoint.
Track users and service-to-service operations.
Choose two designs.
Use short-lived service credentials and least privilege, and log user, app, model, and action while authorizing internal calls.
Detailed explanation
Long-lived secrets are not spread to callers.
Long-lived secrets are not spread to callers.
Internal calls remain attributable and controlled.
Internal calls remain attributable and controlled.
A compromised internal actor can misuse the endpoint.
A compromised internal actor can misuse the endpoint.
Broad privilege can leak.
Broad privilege can leak.
Try it yourself
An example you can run in a temporary verification environment.
AWS公式AIF-C01 Domain 5.1のIAM、推論エンドポイント、監査を確認する。Expected result
ネットワーク内の通信も認証・認可・監査が必要な理由を説明できる。Key points
- Short-lived credentials
- Authorization
- Audit
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.