If you read the fine article, you'll see that the approach includes a non-LLM controller managing structured communication between the Privileged LLM (allowed to perform actions) and the Quarantined LLM (only allowed to produce structured data, which is assumed to be tainted).

See also CaMeL https://simonwillison.net/2025/Apr/11/camel/ which incorporates a type system to track tainted data from the Quarantined LLM, ensuring that the Privileged LLM can't even see tainted _data_ until it's been reviewed by a human user. (But this can induce user fatigue as the user is forced to manually approve all the data that the Privileged LLM can access.)

One would have to be relatively invisible.

Non-deterministic security feels like a relatively new area.

Yes they can