One ChatGPT share link could expose a victim’s private conversations
Parameter Labs found that opening a malicious public ChatGPT share link could let an attacker run JavaScript inside the signed-in session, read private conversations, and act through authenticated APIs. The chain combined ChatGPT’s HTML Preview with a MathLive message listener that accepted attacker-controlled HTML, bypassing the sandbox and content security policy. OpenAI fixed it on October 26 and classified the report as P1.