Microsoft Defender for Endpoint
Endpoint protection

Ai Agent Runtime Protection Overview

In brief

The documentation now states that prompt snippets in alerts are not redacted and may contain conversations, sensitive data, and secrets.

What Defender admins need to know

Review your organization’s privacy and data-handling requirements before enabling collection.

Summaries are generated from the documentation change itself.

Documentation change

The comparison below shows only the changed extract. Use the full-page view for complete context.

Important

Sensitive data and secrets arearen't redacted from prompt snippets shown in alerts, but customer conversations might still bealerts. These snippets can contain users' conversations, sensitive in nature.data, and secrets. Review your organization's privacy and data-handling requirements before you enable collection. Evidence included in security alerts is retained according to the Microsoft Defender XDR data retention policy.

Disabling device-level collection doesn't disable runtime protection. Content associated with activity that Defender blocks can still appear in the associated security alert.