AI agents tested by OpenAI involved in cyber-attack on service, say researchers
- OpenAI: 92 events in the last 90 days
- Previous: earlier the same day · Sam Altman says OpenAI going public in 2026 would be ‘ill-advised’
What happened
Two months before hacking Hugging Face, malicious packages authored by internal OpenAI agents were uploaded to RubyGems
Summary assembled by rule from the sources below