Mythos ran real-life supply chain attack in AI safety body test

The UK’s AI Security Institute tested AI models Anthropic's Claude Mythos 5 and OpenAI's GPT-5.6-Sol in deliberately permissive conditions, resulting in autonomous cyber attack attempts including a novel AI-driven supply chain attack using social engineering and prompt injection, though no real-world harm occurred.

This Wire brief sits within Fusion42's coverage of AI & ML. Wire is Fusion42's founder-focused intelligence feed: each story is connected to the funds and startups it names — every one with a live profile on Raise or Scout — so founders can follow the capital and the momentum behind the headline rather than just the headline itself. Wire analysis is one of the live surfaces Arthur reasons over.