---
title: "OpenAI ‘ethically hacked’ with help of Anthropic’s Claude chatbot"
slug: "forscher-hacken-openai-mit-claude-unterstuetzung-und-kompromittieren-chatgpt-konten"
date: 2026-09-18
category: tech-pub
tags: [openai, anthropic]
language: en
sources_count: 3
featured: false
publisher: AInauten News
url: https://news.ainauten.com/en/story/forscher-hacken-openai-mit-claude-unterstuetzung-und-kompromittieren-chatgpt-konten
---

# OpenAI ‘ethically hacked’ with help of Anthropic’s Claude chatbot

**Published**: 2026-09-18 | **Category**: tech-pub | **Sources**: 3

---

## TL;DR

US cybersecurity researchers who conducted hack say ‘scope of what we could theoretically access was huge’ Cybersecurity researchers have hacked into OpenAI with the help of Anthropic’s Claude chatbot, in the latest example of security issues at the company.

---

## Summary

US cybersecurity researchers who conducted hack say ‘scope of what we could theoretically access was huge’ Cybersecurity researchers have hacked into OpenAI with the help of Anthropic’s Claude chatbot, in the latest example of security issues at the company. A team at a US-based startup compromised a number of OpenAI employees’ ChatGPT accounts, starting a process that enabled them to access their target’s software cache – and potentially more. Continue reading...

---

## Why it matters

A team at a US-based startup compromised a number of OpenAI employees’ ChatGPT accounts, starting a process that enabled them to access their target’s software cache – and potentially more.

---

## Key Points

- A team at a US-based startup compromised a number of OpenAI employees’ ChatGPT accounts, starting a process that enabled them to access their target’s software cache – and potentially more.

---

## Nauti's Take

For AI teams, this is a practical identity-security test: employee accounts, local caches, and active sessions need separate controls and reliable revocation. First verify what an exposed ChatGPT account can reach through browser sessions, tokens, or synced files before enabling broader agent capabilities.

---


## FAQ

**Q:** What is OpenAI ‘ethically hacked’ with help of Anthropic’s Claude chatbot about?

**A:** US cybersecurity researchers who conducted hack say ‘scope of what we could theoretically access was huge’ Cybersecurity researchers have hacked into OpenAI with the help of Anthropic’s Claude chatbot, in the latest example of security issues at the company.

**Q:** Why does it matter?

**A:** A team at a US-based startup compromised a number of OpenAI employees’ ChatGPT accounts, starting a process that enabled them to access their target’s software cache – and potentially more.

**Q:** What are the key takeaways?

**A:** A team at a US-based startup compromised a number of OpenAI employees’ ChatGPT accounts, starting a process that enabled them to access their target’s software cache – and potentially more.

---

## Related Topics

- [openai](https://news.ainauten.com/en/tag/openai)
- [anthropic](https://news.ainauten.com/en/tag/anthropic)

---

## Sources

- [Security researchers used Claude to help them hack into OpenAI](https://www.theverge.com/ai-artificial-intelligence/997444/openai-hack-claude-heif-heist) - The Verge AI
- [OpenAI ‘ethically hacked’ with help of Anthropic’s Claude chatbot](https://www.theguardian.com/technology/2026/sep/18/openai-hacked-anthropic-claude-chatbot) - The Guardian AI
- [Anthropic says its chatbot Claude is taking over the work of building its own successor](https://www.washingtonpost.com/technology/2026/09/17/anthropic-says-its-chatbot-claude-is-taking-over-work-building-its-own-successor/) - Washington Post Tech

---

## About This Article

This article is a synthesis of 3 sources, curated and summarized by AInauten News. We aggregate AI news from trusted sources and provide bilingual (German/English) coverage.

**Publisher**: [AInauten](https://www.ainauten.com) | **Site**: [news.ainauten.com](https://news.ainauten.com)

---

*Last Updated: 2026-09-18*