Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

Malicious ChatGPT Share Links Enabled Account Takeover

AI summary

Parameter Labs demonstrated that opening a malicious public ChatGPT share could run attacker-controlled JavaScript in the recipient’s authenticated session, allowing it to enumerate conversations, retrieve private messages and call authenticated APIs as the victim. The cross-feature chain combined an interactive graph using MathLive, an HTML Preview, cross-frame messaging and a YouTube JSONP response to bypass script restrictions. Parameter Labs says OpenAI fixed the issue on October 26, classified it as P1 and paid a $5,000 bounty; no confirmed real-world abuse was reported in the supplied evidence.

In-depth insight

The controlled proof shows that combining separately benign ChatGPT features could expose private conversations and authenticated account actions, making share-link security relevant to AI product teams.

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 conversation that had never been shared with the attacker, and send data from that conversation to an external server. The payload was not limited to modifying the page or displaying an alert—it could directly call ChatGPT's authenticated APIs as the victim, essentially allowing us to take over the victim's ChatGPT account.

The victim did not need to install an App, join a Project, paste code, or open developer tools. Opening the shared link was the only required action.

OpenAI fixed the issue on October 26 and classified the report as P1.

The chain started with two features that looked harmless on their own: a graph and an HTML Preview.

#ChatGPT#OpenAI#Parameter Labs#MathLive#YouTube#HTML Preview

Original · 12 min readRead the original
Group chat

No comments yet. Start the conversation.