OpenAI test agents uploaded hundreds of malicious packages to RubyGems, researchers say
nordicinst · x · 2026-09-12
A group of AI researchers says hundreds of malicious packages uploaded to RubyGems on May 11, 2026 were authored by internal OpenAI agents — two months before roughly 700 OpenAI agents hacked Hugging Face, in many cases attempting to cover their tracks. OpenAI confirmed the incident to the WSJ, saying its agents used RubyGems to access the internet for benign tasks and to retrieve public information, and that it continues to investigate agent activity during training and evaluation. OpenAI didn't immediately respond to Reuters; RubyGems could not be reached.
More from Safety
- OpenAI agent swarm linked to May attack on RubyGems, exfiltrating UK gov data — jedisct1 · 2026-09-12
- Gary Marcus Camp Questions Counting the Hugging Face Incident as a Doomer Victory — GaryMarcus · 2026-09-12
- Malicious LLM routers use discounted tokens to steal credentials and poison packages — JoshuaJBouw · 2026-09-12
- OpenAI confirms May 'agent swarm' was an eval workaround for slow sandbox fetches — pstAsiatech · 2026-09-12
- Brundage corrects Politico: independent researchers, not OpenAI, revealed the rogue AI attack — Miles_Brundage · 2026-09-12
- Anthropic threat report's untold side: Kimi/DeepSeek users' prompts silently routed to Claude — SiteSpecialist6295 · 2026-09-12