A Shared ChatGPT Link Could Run Attacker Code in Your Session and Read Private Chats

Summary

Parameter researchers showed that a malicious ChatGPT share link could run attacker code inside the session of anyone who opened it, letting the attacker read private conversations. OpenAI received the report on October 18, fixed the flaw eight days later, and rated it P1, its most serious category.

Mitigation

OpenAI fixed the issue across two versions of ChatGPT's web frontend, and by October 26 both versions rejected the messages the attack relied on.

Related items

• MediumAppraisal by AI: Model-driven victim prioritization in the VOLTA infostealerSame vendor · Cisco Talos Blog
• InfoSam Altman says it’s better for RAM to be in a data center than on your deskSame vendor · The Verge (AI)
• InfoThe biggest names in AI are backing a new way to opt out of scrapingSame vendor · The Verge (AI)
• InfoGhost in the machine: how AI is haunting the search for the supernaturalSame vendor · The Guardian Technology
• InfoSam Altman sympathizes with mathematicians, but says OpenAI’s math onslaught won’t stopSame vendor · The Verge (AI)