Microsoft API in Azure AI Content Safety that analyses user prompts and supplied documents for adversarial instructions, returning attack-detected flags for direct user prompt attacks and indirect attacks embedded in external content. It is a detection endpoint that applications must act on rather than an enforcement gateway.
commercial · generally available · Research snapshot 2026-09-06
Show me a shieldPrompt call flagging an indirect injection hidden in an uploaded document, and how the calling agent enforces a block based on that response.
Capabilities and evidence
Support labels reflect the supplied research. Documentation and vendor claims are not independent product tests. “Not established” means the researcher did not find support; it does not prove a capability is absent.
Documented by provider
Prompt Shields is a unified API that detects and blocks adversarial user input attacks on LLMs, covering user prompt injection attempts to circumvent system rules and document-based indirect attacks with hidden instructions in external material.
Limit: Detection is scoped to prompts and documents; tool calls, agent plans and outbound data flows are not covered.
The API endpoint contentsafety/text:shieldPrompt returns attackDetected booleans for the user prompt and each document, with configurable thresholds for filtering.
Limit: Enforcement depends on the calling application; the API itself does not block traffic.