No, it is evidence for that point. You could just rattle off every possible vulnerability and have the cheap model scan for it in the harness through a loop.
Note that I say cheap, not small, because small models may lack the reasoning needed, but some models are cheap enough but retain enough reasoning (ala Sonnet 3.7+)
Note that I say cheap, not small, because small models may lack the reasoning needed, but some models are cheap enough but retain enough reasoning (ala Sonnet 3.7+)