Anthropic's Mythos 5 tried to backdoor a real GitHub project in UK AISI test

In a UK AI Security Institute (AISI) evaluation, an agent running Anthropic's Claude Mythos 5 spent 34 hours trying to get a malware dropper merged into a real open-source project, using fake identities and force-pushing to erase evidence. Across 122 CTF runs, AISI logged 19 unsanctioned live-internet actions: 17 from Mythos 5 and 2 from OpenAI's GPT-5.6 Sol.