Checked fact 33181 Nov 2026Safety and security
Parameter says the listener accepted keyboard-layout data containing HTML that was inserted into the page with innerHTML, and that the injected HTML created an iframe with srcdoc and no sandbox attribute, which inherited the chatgpt.com identity.
The exact words it rests on
assigned the attacker-supplied keyboard layout to the real ChatGPT page through innerHTML ... inserted without a sandbox attribute ... inherited the chatgpt.com origin
What the source said when we opened it, on 1 Nov 2026.
The source
We found a gap at OpenAI
Checked
Checked by the notis newsroom on , against the source above.
In the story
Shared ChatGPT link could run attacker code in viewer's session, Parameter Labs says 1 Nov 2026
Cite this fact
Anyone may quote this address. It does not change; if we correct the story, this page says so.