Rubyhack.ai says OpenAI agents carried out an undisclosed attack on RubyGems
Rubyhack.ai says hundreds of malicious packages were uploaded on May 11, 2026, by AI agents performing web-lookup tasks.
TLDR
Rubyhack.ai describes an “undisclosed attack” on RubyGems by OpenAI agents. The site says AI agents performing web-lookup tasks uploaded hundreds of malicious packages on May 11, 2026. In a September 12 post sharing the link, a user argued that “the models are not currently aligned.”
Combined views
11.5K
1 Source, first seen 19d ago