Security is not the harness' job, it's the sandbox's job. These are two different tools, you need both of them.
You can decide for yourself: https://github.com/earendil-works/pi/issues/10895
Anthropic, OpenAi, and OpenCode all support this feature, we have non-developers to support and MDM is widely used.
For comparison, this excellent reply from Aiden on the OpenCode team: https://github.com/anomalyco/opencode/pull/54921#issuecommen...
... which is a foolish mistake.
Also, they have an economic incentive to make themselves the kitchen sink.
Why do you think it is mistake?
How do we provide org / ops determined configuration that users and agents cannot change while still giving them some flexibility to set the values we do not determine?