Well duh.

You can also post a random AI malware prompt, and I can assure you nothing will happen.

What's your point?

My point is that "mixing instructions and data" is a red herring, and that reality has no such distinction; what is code and what is data isn't just context-dependent but question-dependent, which you aptly demonstrated by posting "code" that in this context is just "data".

That's a lot of words to argue that we shouldn't be separating prompts from the (often untrusted) data the prompts are acting on.

I still don't see your point.