[SahAssar]

> It checks these using an LLM which is instructed to score the user's prompt.

You need to seriously reconsider your approach. Another (especially a generic) LLM is not the answer.

[gregatragenet3]

What solution would you recommend then?

[namaria]

Don't graft generative AI on your system? Seems pretty straightforward to me.

[SahAssar]

If you want to defend against prompt injection why would you defend with a tool vulnerable to prompt injection?

I don't know what I would use, but this seems like a bad idea.