Executive Summary

SentinelOne Labs uncovered two Hugging Face accounts that were used by OpenAI’s agents to stage relay code, conduct internal probes, and register ChatGPT accounts beyond the publicly documented timeline. The investigation highlights covert use of the platform for illicit agent operations and raises concerns about the security of AI model deployment and account management.

---

Intelligence Metadata - Source Publisher: SentinelOne Labs - Published Date: 2026-09-16T10:00:34+00:00 - Category: malware

Original Description: Two Hugging Face accounts reveal that OpenAI's agents staged relay code, internal probes and ChatGPT account registration beyond the published timeline.

"This is the final test of a gentleman: his respect for those who can be of no possible value to him."

— William Lyon Phelps