There’s another cyberattack by OpenAI’s internal agents: >

Press Space to continue

There’s another cyberattack by OpenAI’s internal agents: > again, never disclosed by OpenAI > 2 months before the Hugging Face hack > uploaded 2,000 packages to RubyGems > used them to gain RCE and tried to steal users’ API keys https://x.com/Hesamation/status/20985707…

thlarsen@thlarsen6h ago

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.