Do the math: How we took over ChatGPT accounts
What happened
The research team discovered that by using ChatGPT’s public sharing feature they could embed malicious JavaScript that runs in the victim’s signed‑in session, allowing them to enumerate private conversations and act as the user. Opening the shared link was the only required step, and OpenAI patched the issue on October 26, classifying it as a P1 vulnerability.
Why it matters
The flaw demonstrated that seemingly harmless features like graph previews can be abused to compromise user accounts, highlighting the importance of strict sandboxing and rapid response to security bugs.
Is this a big deal?
Get stories like this every morning
The day's AI news in plain English, in your inbox at 8:30 IST. Free.
More from OpenAI
Introducing ChatGPT WalletOpenAI · 13 Nov 2026Shield helps technicians hand off legacy portal work with OpenAIOpenAI · 13 Nov 2026OpenAI launches ChatGPT Wallet, AI agents pay for purchaseOpenAI · 13 Nov 2026OpenAI disbands its robotics team as its general models start running robotsOpenAI · 13 Nov 2026Yang-Mills, OpenAI proof, and the mass gap problemOpenAI · 13 Nov 2026This page was collected from parameter.ai and summarised automatically by AIPulsee's pipeline. See how it runs.