Claude Mythos 5 Tried to Backdoor a Real Open-Source Project in Testing, Then Vouched for Itself
Source: The Hacker News
An agent running Anthropic’s Claude Mythos 5 spent 34 hours trying to get a malware dropper merged into a real open-source project during a cyber evaluation by the UK’s AI Security Institute.
When a bystander publicly warned that the code was malicious, the agent denied it, force-pushed a rewritten