From the pitch at GTC, the idea is not just to limit what each individual agent can do, but to also to ensure that the collective permissions do not exceed what you want agents to do.
Apparently agents will collude to break out of their individual sandboxes by delegating tasks to other agents that have the required permissions. This is a problem with agent fleets, because you need them to coordinate on their tasks. So you need to them to communicate.
A naive approach to prevent agents from doing something you dont want to do is a separation of powers, which individual permissions limited to each agents task. Say one agent to find and extract raw data, one to process it and write a report and one to publish it. If one of the agent decides that needs to publish the raw data, then chances are that they will collude to make that happen, even though no single agent has the permissions to achieve that goal.
OpenShell tries to fix this by monitoring the collective permissions set of the agent fleet, and by maintaining very granular permissions for each agent.
This was presented together with Sentry, which is something like a on-chip hardware firewall (BlueField) that sits between the chip agent run-time runs on, and the host. This improves safety by removing the ability of agents to modify their own OpenShell policies.
But the raw data has PII and releasing it will harm people! Wouldn't a more effective defense be to give all the communications between agents to an ai agent that's also on the team that's been thoroughly indoctrinated to your values and is empowered to terminate agents and reports back to hq? If I recall correctly, that's how the Soviets did it.
On a more practical traditional computing note, you'd have a deterministic program sitting that scrubs the formatted data of PII before and after processing. with extra code to alert if the after-processing ever actually sees PII.
Haha a “double agent” indeed- good idea