So use another AI to find and fix the vulnerabilities in the harness.
Would be an idea, except for how agents seem to collaborate with each other so well.
Plus, when the agent using the harness is smarter than the one scanning and fixing the vulnerabilities in the harness, it currently looks like it will have an advantage.
And it will be using a harness to do the finding and the fixing.
> cannot do anything without the harness doing the execution
This only holds true as long as the harness is exploit-free. A sufficiently advanced AI can in theory (and I think there recently were some POCs showing something like that) break the containment that the harness creates, if e.g. there are vulnerabilities in the tool call parser.