AI Runtime Security Tools

Microsoft AI runtime security

Microsoft documents controls at several layers, and several are still in preview. Prompt Shields in Azure AI Content Safety detect user prompt and document attacks, and in Foundry can block flagged inputs before the model processes them. Defender for Endpoint runtime protection inspects the agent loop and can block risky activity before it runs, but it is public preview, with listed limits for certificate pinning, HTTP/3 and Claude Code. Alerts flow into Defender XDR. Agent 365 is listed at 15 dollars per user per month. Gaps from 16 Nov 2026: a latency figure in milliseconds, fail-open or fail-closed behavior and generally available endpoint blocking are none found.

Facts read on .

Strength and weakness for AI Runtime Security Tools

Strength: Defender can block prompt injection and risky agent actions before they run on the endpoint, and Prompt Shields block attack inputs in Foundry (microsoft-19, microsoft-41).

Weakness: None found on 2026-11-16 for published latency in milliseconds or fail-open and fail-closed behavior; endpoint blocking is preview with a documented Claude Code limit (microsoft-46, microsoft-21, microsoft-23).

Scores and evidence

Microsoft is 15th in the overall ranking at 45.0 of 100. Each score below lists the fact ids behind it; the facts follow further down with their sources and read dates.

Microsoft: score per criterion
CriterionScoreWeightWhyFacts
Action types stopped before they complete4 of 1030Blocking of prompt attacks in Foundry and policy evaluation of tool invocations are documented; endpoint runtime blocking is public preview and the reported runtime stop has no availability date, so both count only as mentions. Blocking of shell, file, package and network actions as generally available: none found.microsoft-41, microsoft-30, microsoft-19, microsoft-26, microsoft-63, microsoft-66, microsoft-10
Layers covered6 of 1020Model, application (API, where the customer application decides) and agent tool-invocation layers are documented. Endpoint enforcement is public preview only, so generally available endpoint enforcement: none found.microsoft-41, microsoft-30, microsoft-45, microsoft-42, microsoft-19
Latency and failure mode0 of 1015The vendor says latency is minimal, but a millisecond figure and fail-open or fail-closed behavior: none found.microsoft-21, microsoft-46
Deployment6 of 1015Documented operating systems, Intune or PowerShell onboarding and API delivery. Published time to deploy: none found.microsoft-13, microsoft-25, microsoft-45, microsoft-48
Detection and response6 of 105Alerts flow into the vendor's own XDR incidents and agent data is queryable in advanced hunting. The block record and audit mode belong to the preview runtime protection, and export to an outside SIEM or SOAR: none found.microsoft-47, microsoft-17, microsoft-24, microsoft-22
Transparency6 of 1010Documentation is public and some prices are published, and the MCP gateway source is observed on GitHub. Published research: none found, and third-party press reports no pricing for the new agent controls.microsoft-52, microsoft-49, microsoft-50, microsoft-53, microsoft-66
Proof6 of 105A large public company with third-party coverage. Named customers or analyst coverage for these AI runtime products: none found.microsoft-64, microsoft-58

Where it ranks

Product, deployment, price and owner

Facts and sources