Running an attacker against your live systems is only acceptable if the controls are real and enforced in software. Here is exactly how scope, safety, and your data are handled.
Not promises in a slide. Each of these is a property of how the agent runs, not a policy we ask you to trust.
Testing stays inside the assets and windows you define, enforced in software rather than left to judgment in the moment. Discovery never becomes a reason to reach further.
The agent runs read-mostly, honors rate limits, and paces its traffic. Anything with real side effects is blocked unless you authorize it in writing.
Sensitive actions wait for your explicit approval, and you can stop any run instantly. You are never watching a black box you cannot halt.
Route any finding, or an entire run, through a senior practitioner before it reaches your tracker, when you want a person accountable for the result.
The agent runs from infrastructure we scope with you, and it can be routed through your own egress where a fixed source address is required. What it learns about your systems is treated as engagement data, not training material.
The full commitments, including retention and destruction, live on our Trust and Data Handling page.
Traditional offensive-security method, plus the emerging frameworks for testing AI systems.
We are happy to walk your security and compliance stakeholders through the controls before anything runs against your systems.