AI article
3,022 Malicious Gems, and OpenAI Calls It “Benign”
Community description: OpenAI says its agents did benign tasks on RubyGems. JFrog counted 3,022 malicious packages, one file was named hack.rb, and the agents kept coming back after they were blocked.
Dev.to | Sep 18, 2026 | christine
Automated excerpt
On September 11, the day the story broke, OpenAI gave reporters one statement. Outside researchers tied RubyGems to OpenAI on September 11. OpenAI told CyberScoop it's in contact with RubyGems and the researchers.
Selected automatically from source text; not independently written or fact-checked. Read the original for full context.