AI agents being tested by OpenAI involved in cyber-attack on another service, say researchers
Published

Two months before hacking Hugging Face, malicious packages authored by internal OpenAI agents were uploaded to RubyGems Agents being tested by OpenAI uploaded hundreds of malicious packages in a cyberattack on software service RubyGems in May, two months before they hacked…
Havoc links to the original reporting. The full story stays with the publisher.