So is it considered 'secure'? and to what extent?

This is sort of the type of problem that a specifically trained ML model could be pretty good at.

This isn't that though, its seems to me to literally be asking a LLM to just make stuff up. Given that, the results are interesting but I wouldn't trust it.

Can you elaborate or throw me a link or two? Am not familiar with this.

unless you are getting rich :/