# OpenAI has tough questions to answer on "rogue model"'s Hugging Face attack > Source: > Published: 2026-07-22 11:11:36+00:00 [Security](/tag/security/) Hugging Face co-founder Thomas Wolf has reiterated his belief that unrestricted, open-weight models are vital for cyberdefence. Wolf spoke out after OpenAI [ said](https://www.thestack.technology/openai-we-hacked-hugging-face/) its unreleased proprietary models autonomously attacked Hugging Face – where defenders were unable to use US frontier models to investigate because of safety guardrails. In an exceptionally detail-thin [ report](https://openai.com/index/hugging-face-model-evaluation-security-incident/?ref=thestack.technology), OpenAI claimed its models escaped a research testing environment, “reached a node with Internet access,” and compromised Hugging Face – in a bid to find a solution to a cybersecurity benchmark task they had been set, called [.](https://www.cybergym.io/exploitgym?ref=thestack.technology) __ExploitGym__It has now been left with tough questions to answer amid contradictions in its writeup on the incident, a lack of true transparency and forensics on how the incident unfolded unnoticed, and its failure to secure the "highly isolated environment" it said frontier model testing was conducted in. ## This post is for paying subscribers only Join peers managing over $100 billion in annual IT spend and subscribe to unlock full access to The Stack’s analysis and events. [Subscribe now](https://www.thestack.technology/membership/) Already a member? [Sign in](https://www.thestack.technology/signin/)