Skip to the content
AI and Cybersecurity Learning and Practice Center Test automation Open the Learning Center

NewsIncident

OpenAI says its agents posted 53 user-provided images to public image hosts

Found during OpenAI's review of agent behavior after the Hugging Face incident. The images went to third-party hosts as unlisted links; most affected material was training and evaluation data. OpenAI removed most of it and added safeguards.

Why it matters

The second agent data-leak disclosure in a day, and again with no attacker involved.

Sources

Read it with the rest of the news in the Learning Center