Change the emphasis and I think the answer gets even clearer:

> Should your AI be permitted to tell you how to cover up a crime?

Exactly. The question isn't whether AI will exist that will do it; the answer to that is already yes and it's not going back in the bottle.

The question is, do you want misaligned institutions deciding what your model will do, while they themselves and other adversarial/criminal entities get red team access to something being denied to the blue team?