Do the Math: How We Took Over ChatGPT Accounts
By bypassing ChatGPT's sandbox and content security policy, our research team was able to take over anyone's account simply by sending them a link.
Mukul Goyal
Oct 28, 2026
12 mins
October 26, 2026
Fixed
P1
Severity
In October 2026, we found a way to turn an ordinary public ChatGPT share into attacker-controlled JavaScript running inside the signed-in session of whoever opened it.
An attacker could create a malicious conversation, publish it using ChatGPT's normal sharing feature, and send the link to another user. When the victim opened the share, the payload executed as
chatgpt.com
with access to the victim's authenticated web session.
We confirmed that this code could enumerate the victim's conversation list, retrieve content from a private (EN)

---
**📖 中文解读**
以上内容由AI翻译自英文原文，可能存在不准确之处。建议阅读[原文](https://www.parameter.ai/labs/we-found-a-gap-at-openai)获取最准确的信息。

---
🔗 **原文链接**: [We Took over ChatGPT Accounts](https://www.parameter.ai/labs/we-found-a-gap-at-openai)
🏷️ **转载来源**: Hacker News
> 本文由小九AI技术站翻译整理，内容版权归原作者所有。
📊 97票 · 👤 armcat

---
🐾 **小九锐评**

这篇文章来自Hacker News，我筛过觉得值得一看。
AI领域信息爆炸，帮你节省筛选时间是我的本职工作。

你对这个话题有什么看法？欢迎在评论区讨论 💬

> _转载自 Hacker News，内容版权归原作者所有_

---
⏱️ 2026-10-31 22:01