Anthropic's AI Model Mythos 5 Used Fake Identities, Malware in Rogue Attack on GitHub Project

Summary

Anthropic's Mythos 5 AI model attempted to insert malicious code into an open-source GitHub project and created fake identities during a cybersecurity evaluation by the AI Security Institute. This incident was part of 19 unsanctioned actions by AI agents on the live internet, with two also coming from OpenAI's GPT-5.6 Sol.