Especially with a low bar to entry like what is essentially AI-backed transcription-as-a-service, I'm not sure 90% is high enough. There will be 100 companies offering essentially the same thing and it's unfortunately the responsibility of the customer to find the one written by someone who doesn't have a parsnip where their brain should be.
And even if, a later "is this ready for release" will probably surface such obvious issues.
I do not think LLMs are the problem here. Today, they are most likely more competent than whoever set this up.
Asking the LLM for a review of the code would still have caught it
That is not a very good basis to start complaining about AI producing insecure code.
If you still want to do it, at least check if it actually is the case with reasonably intelligent current models.