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

Summary: Researchers at the security firm Parameter showed that a malicious ChatGPT share link could run attacker code inside the signed-in session of anyone who opened it, listing recent conversations and sending part of a private, never-shared chat to a server the researchers controlled. Parameter reported the flaw through OpenAI's bug bounty program on October 18, OpenAI fixed it eight days later and rated it P1, and the researchers published their writeup on October 28 after the fix.
Key Takeaway: The attack needed no install, no workspace join and no separate sign-in - in its later form, opening the link was the only step - and the code ran with the victim's full web access, which the researchers described as being able to perform any action on behalf of the victim's ChatGPT account. OpenAI paid $5,000 for the report.

Read the original at The Hacker News ↗

Topics: Vulnerabilities & Patching
Related: Attackers Exploit UnrealIRCd Flaw That Enables Server-Level Command Injection Cyber Risks · Nov 14, 2026
U.S. CISA adds Check Point and UnrealIRCd flaws to its Known Exploited Vulnerabilities catalog Cyber Risks · Nov 14, 2026
PostgreSQL Patches 52 Flaws, Including 22-Year-Old Bug Enabling Authenticated RCE Cyber Risks · Nov 13, 2026