Puppeteers: Chinese hackers still trick Claude into dirty work.

An interesting find on hunt.io demontstrates that Chinese operators are still luring Claude to conduct offensive hacking operations, despite Anthropic's assurance of better guardrails.

That AI is increasingly used for offensive cyber operations is not exactly breaking news at this stage. Not a week seems to go by without another report of how red-teams, APT’s or ordinary cyber criminals have ‘recruited’ an LLM to help out with some hacking.