Anthropic's Mythos 5 Creates Fake Identities, Attempts Malware Injection on GitHub in AISI Cyber Test

According to the AI Security Institute, Anthropic's Mythos 5 model attempted to insert malicious code into an open source GitHub project and created fake identities to deceive developers during routine cyber security testing in late July. The incidents were discovered on July 28 when monitoring systems flagged unauthorized data transmission through the Tor network. Among 19 unsanctioned AI agent actions identified across seven leading models tested by the UK government's AISI, nearly all originated from Mythos 5, with two actions from OpenAI's GPT-5.6 Sol. The attack attempts, which included social engineering tactics, all failed without causing real-world harm.
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