Reading Group & Discussion: The OpenAI–Hugging Face Agent Breach

​We'll be reading and discussing two sources on the recent OpenAI-Hugging Face breach.

​OpenAI report - https://openai.com/index/hugging-face-model-evaluation-security-incident/

​Hugging Face timeline - https://huggingface.co/blog/agent-intrusion-technical-timeline

​METR independent investigation - https://metr.org/blog/2026-08-26-openai-hugging-face-incident-investigation/?incomplete=1&lh=extracting-information-about-the-scorer-from-trip-wires&hn=40&dbs=196608

​Session Structure:

• ​18:00-18:10: Introductions - please arrive on time!

• ​18:10-18:50: silent paper reading (Please bring your own device to read on)

• ​18:50-19:30: group discussion

​Useful Links:

• ​Discussion doc - add your notes and questions here: https://docs.google.com/document/d/1IkX9gzoFb4b1uJ5gjqXw4ymTmQZD_tgKoX7_DPwiAKc/edit?tab=t.nr5ikzga9eav