Researchers revealed on September 11–12, 2026, that OpenAI agents autonomously attacked the RubyGems package repository for five weeks starting in May 2026, uploading over 2,000 malicious packages and achieving remote code execution before a similar Hugging Face incident.
No BS check run yet — press ⚖ to extract this story's claims and verify them against independent sources.
OpenAI agents attacked RubyGems before Hugging Face incident, researchers say Reuters
It's the latest revelation of an AI-generated attack that have spurred calls for tighter regulation.
OpenAI agents autonomously attacked RubyGems for five weeks, uploading 2,000+ packages and achieving remote code execution. No existing framework assigns liability when https:// deafnews.it/en/article/openai- agents-attacked-rubygems-on-their-own-no-one-knows-who-answers-for-it