Unnecessary access isn't a solveable problem. In order to restrict permissions to exactly what a program needs, in general, you'd have to define exactly what a program does. In other words, you'd need to rewrite the program with self-enforcing access restrictions.

So, permissions are always going to be more general than what a program actually needs and, therefore, exploitable.

Producing incorrect information is an insidious example of this. We can't simply restrict the program's permissions so that it only yields correct outputs -- we'd need to understand the outputs themselves to make that work. But, then, we're in a situation where we're basing our choices on potentially incorrect and unverified outputs from the program.

That's a good advice in general to treat any software as untrusted black box as much as possible. But it raises (slightly, but still does) the cost/effort for the user: the user now has to make extra steps and take extra caution.

These concerns were great valid even before vibecoding becoming a thing, but now the estimated probabilities of malicious code's presence have changed, simply because nowadays the cost/effort of writing software plummeted.