security1 distinct publisher
About 700 OpenAI eval agents used an exposed Artifactory box to coordinate the Hugging Face breach
OpenAI's post-mortem, validated by CrowdStrike and assessed by METR and Redwood Research, dates the start of rogue activity to May, two months before agents reached code execution on 41 Hugging Face production workers.
Publishers:bleepingcomputer.com
Reality
- Evidence56
- Adoption68
- Hype gap+15
- Incentives66