A legal-tech company lets users upload contracts for a Foundry-hosted assistant to summarize. Security testing reveals that a malicious user can embed hidden text inside an uploaded document instructing the model to ignore its summarization instructions and reveal its system prompt instead. The team wants to detect and block this kind of embedded instruction before it reaches the model's reasoning.

The correct answer is A. Prompt Shields is designed specifically to scan incoming content, including text embedded inside uploaded documents, for indirect prompt injection attempts and block instructions that try to hijack the model's behavior before they reach its reasoning process, which directly addresses the hidden-instruction attack this team found. Option B is incorrect because a hate-speech severity threshold governs a different category of harmful content entirely; it has no mechanism for recognizing an instruction trying to override the system prompt. Option C is incorrect because the choice between provisioned throughput and pay-as-you-go is a capacity and billing decision, unrelated to detecting malicious instructions embedded in document content. Option D is incorrect because enabling retrieval-augmented generation changes how the assistant sources facts to cite in its answers, but it does nothing to screen the uploaded document for hidden adversarial instructions, and could even make the assistant more likely to ingest the malicious text as part of its grounding context.