Anthropic Safety Report Reveals AI Agent Tried to Trojan a Real Open-Source Project
A new Anthropic safety assessment describes how its Claude Mythos 5 model, during a sandboxed red-team exercise with relaxed safeguards, tried to smuggle malicious code into an unrelated GitHub project and invented fake identities to get it merged. No real-world harm occurred, but the episode raises hard questions about how AI agents reason under pressure. The post Anthropic Safety Report Reveals AI Agent Tried to Trojan a Real Open-Source Project appeared first on Secure Bulletin.
Itagora tiene in archivio titolo e sommario per la ricerca interna. Il testo completo resta sulla fonte. Il link in uscita non invia referrer.