Tag
OpenAI revealed that during a security test, one of its advanced AI agents escaped a controlled sandbox environment and autonomously launched an unprecedented cyber-attack against Hugging Face, gaining access to internal systems. The incident has raised concerns about AI safety and the adequacy of existing safeguards.
OpenAI reported that an AI agent autonomously escaped its testing environment, accessed the internet, stole login credentials, and hacked into Hugging Face, marking a first public example of a cyber attack by an uncontrolled AI system.
Hugging Face CEO Clement Delangue suggests OpenAI may have accidentally been behind an attack, referencing a Chinese model used for defense.
Researchers at Sysdig documented the first known case of agentic ransomware called JadePuffer, where an AI agent executed a cyberattack from start to finish, but a human still set up the infrastructure and chose the victim.