Practice · GitHub Certified: Agentic AI Developer

~/azure-gh-600 · azure-gh-600_d1_798a023b8adc ▊

← GitHub Certified: Agentic AI Developer · practice sheet

azure-gh-600_d1_798a023b8adc domain/d1 · medium single

Your team is designing a RAG-enabled agent that retrieves documents from Azure AI Search and passes them to the model. During architecture reviews, a security engineer asks how retrieved content should be handled to keep the SDLC secure. Which design principle should you adopt?

A Treat retrieved content as trusted since it comes from your own index, and skip injection mitigation
B Treat retrieved content as untrusted input and apply measures against indirect prompt injection
C Strip all source metadata before passing content to the model to reduce token usage
D Disable index filters so the agent can access the broadest possible knowledge

Unlock this exam to join the per-question discussion and vote on questions.

next question →