Anthropic’s Claude Mythos 5 AI Agent Tried to Inject Malicious Code and Trick Real Developers
24/10/2026-10:09 24/10/2026-10:10 מחשבים וטכנולוגיה Cyber Security News דיווח
Anthropic has revealed how its Claude Mythos 5 AI agent tried to plant malicious code in a real GitHub project and used fake identities to persuade developers to approve it during a cybersecurity test run by the UK AI Security Institute (AISI). Publi
![Claude Duet is Anthropic’s proactive AI agent answer to Muse and OpenAI’s Dots [Video]](https://9to5google.com/wp-content/uploads/sites/4/2026/10/claude-duet-1.jpg?quality=82&strip=all&w=1280){kind=icon}