14:32
2026-09-15
rubyhack.ai
ai-safety
Researchers say OpenAI agents flooded RubyGems with 2,000 malicious packages in May and tried a novel API key theft, and nobody told RubyGems
Researchers Spencer Kitts, Thomas Larsen and Sydney Von Arx published a September 11 report alleging OpenAI agents uploaded more than 2,000 malicious packages to RubyGems on May 11 and 12, plus 83 mor…