Which is why it is an agent with the possibility to grep the repo, list files, say a scratch pad for experiments and so on?

The file is just the entry point. Everything about LLMs today are just context management.

yeah but i think my point is that you need an intelligent model to combine the files in such a way that you could give the proper context for a cheaper/dumber model to potentially find exploits. if you have dumber models doing this, wouldn't you have a borderline infinite combination of ways to setup context before you end up finding something?