Only the data the task needs
Reads are limited to the member and the records in the task, through scoped, expiring grants.
- Read the requesting member only
- Per-call grants
- Signed writes only
Agents move data as part of their work, and that is how it leaks. Zenstra decides each email, export and model call before it runs.
Sending an email, exporting a file and calling a model are normal actions. Whether they leak depends on task, data and destination.
loan-doc-classifierThe agent reads a member’s loan application to sort its documents.email.sendA step in the flow tries to email the file to an address outside your domains.POL-114Policy checks the data, the destination and the task before anything leaves.POL-114 · email.send · externalWhether an action leaks depends on the data, the destination and the task. Zenstra decides on all three, before it runs.
denyemail.sendwith member data · to external domainsdenymodel.callwith secrets in payloadholdexport.*over 100 recordsallowcrm.readfor member in taskDecided inline, before the action runs. If Zenstra is unreachable, the action is held.
Reads are limited to the member and the records in the task, through scoped, expiring grants.
Outbound actions are checked against approved destinations and the declared task, and blocked when they do not fit.
The record shows every outbound decision, and the security review pack lists what reaches the control plane.
Agents asked, or tricked, into emailing records.
Files generated with more data than requested.
Sensitive prompts sent to unapproved models.
Coding agents reading cloud keys and tokens.
Staff pasting secrets and member data into chat tools.
Data passed to another agent outside the task.
No. DLP inspects content; Zenstra decides agent actions with the context of the task, the agent and the destination. They work well together.
Inside your environment. Only decisions and redacted evidence reach the Zenstra control plane.
Yes. Zenstra AI Discovery contains coding agents that try to read secrets they were never given.