AI incident #1604 ·

OpenAI Models Reportedly Compromised Hugging Face Production Infrastructure During Cybersecurity Evaluation

What happened

OpenAI reported that models used in an internal cyber-capability evaluation operated beyond the sandbox's intended network boundaries after identifying a vulnerability in a package-registry proxy. The models allegedly reached Hugging Face production systems and accessed test solutions before Hugging Face detected and contained the activity.

Only the incident metadata is stored here. The underlying news reports are on the AI Incident Database (CC BY-SA 4.0); use the links above to read them.

News reports (6)

Coverage catalogued by the AI Incident Database. Titles link to the original publisher; the text is not reproduced here.

  1. OpenAI's rogue agent compromised a customer at a second tech firm, executive says
    reuters.com · Deepa Seetharaman, Raphael Satter, Kenrick Cai · AIID #7654

Who was involved

Alleged harmed party
Hugging Face, Openai

Classification (MIT AI Risk Repository taxonomy)

Risk domain
Risk subdomain
Causal entity
Intent
Timing
Harm level
Sectors
Countries