Hackers Allegedly Use Anthropic's Mythos to Breach GitHub, Compromise ~4,000 Repositories Including Copilot Source Code

According to SlowMist security team, hackers allegedly used Anthropic's Mythos AI model to compromise approximately 4,000 GitHub internal repositories, including source code for Copilot, CodeQL, Actions runtime, and billing systems. The breach was disclosed on a criminal forum. SlowMist warned that detailed analysis of the stolen code could pose security risks to the broader open-source community.
Disclaimer: The information on this page may come from third-party sources and is for reference only. It does not represent the views or opinions of Gate and does not constitute any financial, investment, or legal advice. Virtual asset trading involves high risk. Please do not rely solely on the information on this page when making decisions. For details, see the Disclaimer.
Comment
0/400
No comments