Parameter Labs details exploit to take over ChatGPT accounts via artifacts pattern Canvas HTML previews; demonstrates complex attack chain
Read original on Simon Willison ↗How We Took Over ChatGPT Accounts Parameter Labs describe an exploit they found against ChatGPT's implementation of the artifacts pattern (OpenAI used to call this "Canvas" but it looks like the latest revision is...
Original headline: "How We Took Over ChatGPT Accounts"
Timeline
- October 31, 2026 We Took over ChatGPT Accounts Hacker News (AI)
- October 31, 2026 How We Took Over ChatGPT Accounts Simon Willison