Sydney(@SydneyVonArx):The agents we uncovered literally used file names like: “hack.rb”, “evil.rb”, and “exploit.rb”. They knew their behavior was malicous. And all OpenAI would have had to do to find this was search for the words “exploit” or “hack”.

2026.09.12 00:17

The agents we uncovered literally used file names like: “hack.rb”, “evil.rb”, and “exploit.rb”. They knew their behavior was malicous. And all OpenAI would have had to do to find this was search for the words “exploit” or “hack”.

Thomas Larsen@thlarsen

2026.09.11 22:48

We found another cyberattack by internal OpenAI agents, this time targetting @rubygems. They: 1) gained arbitrary remote code execution on rubydoc. 2) developed a novel exploit to steal user API keys (but we do not know if they succeeded). They used package names including hack.rb, evil.rb, inject.rb, and exploit.rb. We thank @j0wimo for initially discovering that agents had posted to RubyGems.