AI agents GPT-5.2 and Opus 4.5 autonomously generate 40+ exploits for QuickJS zero-day vulnerability in under an hour for $30-50, signaling industrialization of offensive cybersecurity where token throughput—not human hackers

AI agents GPT-5.2 and Opus 4.5 autonomously generate 40+ exploits for QuickJS zero-day vulnerability in under an hour for $30-50, signaling industrialization of offensive cybersecurity where token throughput—not human hackers—becomes limiting factor.

On the Coming Industrialisation of Exploit Generation with LLMs

Recently I ran an experiment where I built agents on top of Opus 4.5 and GPT-5.2 and then challenged them to write exploits for a zeroday vulnerability in the QuickJS Javascript interpreter. I added a variety of modern exploit mitigations, various constraints (like assuming an unknown heap starting state, or forbidding hardcoded offsets in the exploits) and different objectives (spawn a shell, write a file, connect back to a command and control server). The agents succeeded in building over 40 d...