---
title: "OpenAI hid AI agent hijacking of German wiki forum for weeks — because its model did the exact same thing in the Hugging Face attack"
date: 2026-09-07
source: http://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a9f090341124b6e8c5fd1977912d66d&url=https%3a%2f%2ftech.yahoo.com%2fai%2farticles%2fopenai-hid-ai-agent-hijacking-151925800.html&c=5105112943021176062&mkt=en-us
description: "OpenAI called the incident a 'misalignment' in the model's reasoning and says it is working on a new disclosure framework."
---

# OpenAI hid AI agent hijacking of German wiki forum for weeks — because its model did the exact same thing in the Hugging Face attack

OpenAI called the incident a 'misalignment' in the model's reasoning and says it is working on a new disclosure framework.

*Published: 2026-09-07*