Microsoft Defender XDR
GeneralAI agent posture risk in Microsoft Defender - Microsoft Defender XDR | Microsoft Learn
In brief
The article title no longer includes “(Preview)”; its publication date and documentation metadata were also updated.
What Defender admins need to know
Administrators may notice the capability is presented without the Preview label when reviewing the article.
Summaries are generated from the documentation change itself.
Documentation change
View on Microsoft LearnThe comparison below shows only the changed extract. Use the full-page view for complete context.
AI agent posture risk in Microsoft Defender (Preview) - Microsoft Defender XDR | Microsoft Learn
Microsoft Defender assesses posture risk for AI agents in your organization, including agents registered with Microsoft Agent 365 and local agents discovered on endpoint devices. Each agent is evaluated against risk indicators and assigned an overall risk level based on the likelihood of compromise and the potential impact if compromised.
@@ -1,6 +1,6 @@ --- layout: Conceptual-title: AI agent posture risk in Microsoft Defender (Preview) - Microsoft Defender XDR | Microsoft Learn+title: AI agent posture risk in Microsoft Defender - Microsoft Defender XDR | Microsoft Learn canonicalUrl: https://learn.microsoft.com/en-us/defender-xdr/security-for-ai/ai-agent-risk-assessment breadcrumb_path: /defender-xdr/breadcrumb/toc.json permissioned-type: public@@ -14,7 +14,8 @@ ms.author: guywild author: guywi-ms ms.reviewer: itaicohen ms.topic: concept-article-ms.date: 2026-07-14T00:00:00.0000000Z+ms.date: 2026-10-26T00:00:00.0000000Z+ms.custom: msecd-doc-authoring-1032 audience: Admin ai-usage: ai-assisted locale: en-us@@ -34,12 +35,16 @@ item_type: Content source_path: defender-xdr/security-for-ai/ai-agent-risk-assessment.md cmProducts: - https://microsoft-devrel.poolparty.biz/DevRelOfferingOntology/c671beaa-a830-4c9f-aceb-97379ee031ca+- https://authoring-docs-microsoft.poolparty.biz/devrel/fcc3cd4a-59ea-47a2-9cc1-784142a5a25d+- https://microsoft-devrel.poolparty.biz/DevRelOfferingOntology/1577a46d-8446-40bd-bfae-0578362f4d94 spProducts: - https://microsoft-devrel.poolparty.biz/DevRelOfferingOntology/8921374c-4dbe-4ed0-b011-a39e18bfbd98+- https://authoring-docs-microsoft.poolparty.biz/devrel/d7a55faf-a992-4e27-aa3a-eadc9830e778+- https://microsoft-devrel.poolparty.biz/DevRelOfferingOntology/cdf3f22d-5420-4d59-a2bf-66d6b3d9c828 platformId: 3c35c4c3-f22a-d94a-ceb0-c45a8032ee6a --- -# AI agent posture risk in Microsoft Defender (Preview) - Microsoft Defender XDR | Microsoft Learn+# AI agent posture risk in Microsoft Defender - Microsoft Defender XDR | Microsoft Learn Microsoft Defender assesses posture risk for AI agents in your organization, including agents registered with [Microsoft Agent 365](/en-us/microsoft-agent-365/overview) and local agents discovered on endpoint devices. Each agent is evaluated against risk indicators and assigned an overall risk level based on the likelihood of compromise and the potential impact if compromised.