Agentic Assistant security - Learn about how the Agentic Assistant is built using responsible AI principles. - Administrator Guide - Cortex XDR - Cortex - Security Operations

Instance and Account admins have full control over the permissions and access that users have to the Cortex Agentic Assistant. Cortex XDR uses Role-Based Access Control (RBAC) to manage access to the chat, as well as access to view, create, edit, delete, disable, and enable Agents and Actions in the Agents Hub.

Agents can only use actions that have been assigned to them, and execution is limited to the user's existing permissions in your Cortex XDR tenant. If a required integration is not active, its commands and any actions that wrap them will not work.

To perform actions in Slack, your Slack email must match your Cortex XDR user email. This ensures the system can strictly follow your assigned permissions (RBAC). If you do not have the required permissions to interact with agents, the system will block the action.

Data is hosted and encrypted by default on a dedicated Google Cloud Platform (GCP) project, and is isolated and protected by your specific IAM permissions. Google's multi-tenant architecture enforces strict data separation between customers.

Actions marked as sensitive require explicit user approval before execution and are never run automatically. This gives you final control over critical or data-modifying steps.

Your prompts and outputs are processed only to generate the immediate response. They are not collected for model training or shared with third parties.

All prompts and responses stay inside that region’s compute boundary, aligning with modern data-residency practices.

You can see how the agent reaches its answer. Click the down arrow next to Plan, to view how the user input was interpreted, the planned steps, and the actions used. You can view JSON artifacts created during the plan execution, when data was retrieved or an object was created.

All actions an agent takes are saved in an audit dataset. You can see which agent ran which action, and which user invoked it.

In addition, all chat logs and actions initiated via Slack are stored in the Cortex XDR database and labelled with a specific Slack prefix or metadata tag.