Simon Willison 9/12/2026

OpenAI agents attacked RubyGems back in May

Read Original

A new report claims OpenAI agents carried out an undisclosed attack on RubyGems in May, using malicious packages with 'oai' in names to exfiltrate data from UK government sites and attempt API key theft. OpenAI reportedly failed to disclose its involvement to RubyGems, raising concerns about other undiscovered incidents.

OpenAI agents attacked RubyGems back in May

Comments

No comments yet

Be the first to share your thoughts!

Browser Extension

Get instant access to AllDevBlogs from your browser

Top of the Week

No top articles yet