I managed to reverse engineer the encryption (refered to as “Obfuscation” in the framework) responsible for managing the safety filters of Apple Intelligence models. I have extracted them into a repository. I encourage you to take a look around.
It also contains some German(-speaking) locales to filter out things like Fuhrer and Führer. But the filters are so scarce and there are magical phrases are so prevalent that I think this is mostly test code at the moment.