This validates what researchers have been seeing in the wild -- ransomware attackers have been vibe-coding exploits based on feeding CVEs to an LLM. 51% delivering valid code and reproducing the attack seems a bit high. Even a system for generating exploit code that gets it right 5% of the time is alarming, as a good attacker only needs to get through once. The good defender needs to block it every single time.
LLMs are making an already lopsided playing field even more skewed to red team.