Isolation, resource and network controls for agent execution environments.
A computer-use agent treats pixels, accessibility data and interface state as both evidence and an action surface. Security must bind intent to effects beyond the screen.
“Internet access” is too broad a permission for an agent. Define destinations, protocols, data-release rules and failure behaviour, then test bypasses against the deployed network path.
An agent becomes especially risky when it can read secrets, ingest attacker-controlled material and communicate or act outside the boundary. Design the workflow to break that combination.
A sandbox limits what compromised execution can reach. Authorisation decides what an authenticated actor may do. Secure agents need both, tested independently and together.
KEEP EXPLORING
Read the method, assumptions and questions to ask.