ChatGPT shared link vulnerability could read private chats, now fixed
Start here
Researchers at security firm Parameter say ChatGPT shared links had a cross-frame messaging vulnerability: a malicious link could execute attacker-supplied JavaScript in the session of a logged-in opener, enumerate recent conversations, read private chats that were never shared, and exfiltrate data to an external server. Initially a single click on Preview was required; later attack versions triggered automatically when the link was opened. The researchers reported it through OpenAI's bug bounty program on October 18; OpenAI reproduced it, raised the severity from P2 to P1, and completed the fix in the frontends of two versions on October 26 (eight days after the report), with no user action required. Parameter said it found no real-world exploitation.
Generated by AI from reports · Updated 15 hr ago
Progress timeline
- WebAI Threat Watch (aithreat.io)· Media coverageОбщая ссылка в ChatGPT открывала личные чаты, OpenAI закрыла баг(opens the original post in a new tab)
- WebAI Threat Watch (aithreat.io)· Media coverageChatGPT, un lien partagé ouvrait les conversations privées, OpenAI corrige la faille(opens the original post in a new tab)
- Profesional ReviewChatGPT previously had a vulnerability that allowed reading users' private conversations, which has now been fixed
Security company Parameter released a report stating that between October 18 and 26 there was an attack that read users' private conversations through ChatGPT shared links, and OpenAI has fixed the vulnerability. The attack link only needed to contain an HTML preview and a chart: when ChatGPT loaded the chart using the MathLive library, its math formula keyboard accepted messages from any other window, inserting unconfirmed HTML, forming an unsandboxed frame that the browser treated as part of ChatGPT and that could even execute JavaScript. Attackers could thereby obtain the full chat list, start new conversations, and send content to an external server, and the report states they could also act in the victim's name. OpenAI fixed the issue directly after setting a $5000 bounty; users do not need to make changes themselves, and can check shared links in the data controls in settings.
- WebAI Threat Watch (aithreat.io)· Media coverageResearchers Discover High-Severity ChatGPT Flaw That Exposed Private Conversations to Attackers(opens the original post in a new tab)
- WebBoannews (Korea)· Media coverage미리보기 한 번에 비공개 대화까지...챗GPT 공유 링크 결함, 8일 만에 수정(opens the original post in a new tab)
- WebAI Threat Watch (aithreat.io)· Media coverageУязвимость ChatGPT позволяла читать ваши личные чаты через ссылку общего доступа(opens the original post in a new tab)
- WebAI Threat Watch (aithreat.io)· Media coverageFaille ChatGPT : un lien partagé exécutait du code(opens the original post in a new tab)
- WebAI Threat Watch (aithreat.io)· Media coverageChatGPT : un lien piégé pouvait exposer des conversations privées, la faille est corrigée(opens the original post in a new tab)
- WebAI Threat Watch (aithreat.io)· Media coverageChatGPT: un enlace compartido podía robar tu cuenta(opens the original post in a new tab)
- CSA Labs ResearchSelectedOne click into someone else's ChatGPT: a cross-frame messaging vulnerability
Researcher Parameter disclosed on October 28, 2026 that a publicly shared ChatGPT conversation link could execute attacker-supplied JavaScript in the session of whoever opened it while logged in, enumerate their recent conversations, read private chats that were never shared, and exfiltrate data to an external server. After reproducing it, OpenAI raised the severity from P2 to P1 and completed the fix on the frontend of two versions on October 26 (eight days after the report), with no user action required; Parameter said no real-world exploitation was found. Initially a single click on Preview was required, after which it was changed to open automatically, so that merely opening the link triggers it, and the payload executes after about 4.5 seconds. The researcher said the same script context could perform any action on the account on behalf of the victim, but this is an inference based on the permissions obtained, and the PoC deliberately limited the exfiltrated content.
- X@read__the__diff· Discussionhttps://thehackernews.com/2026/10/a-shared-chatgpt-link-could-run.html(opens the original post in a new tab)
- WebAI Threat Watch (aithreat.io)· Media coverageОбщая ссылка ChatGPT могла перехватывать сеансы и читать частные чаты(opens the original post in a new tab)
- WebAI Threat Watch (aithreat.io)· Media coverageУязвимость ChatGPT позволяла читать закрытые беседы по ссылке(opens the original post in a new tab)
- The Hacker NewsSelectedA malicious ChatGPT shared link can run attacker code in a logged-in session and read private chats
Researchers at the security company Parameter demonstrated that a malicious ChatGPT shared link can run attacker code in a victim's logged-in session and read private chats; the researchers reported it on October 18 through OpenAI's bug bounty program, and OpenAI fixed it eight days later and rated it the highest severity, P1. The victim only needs to open the link and click Preview once (in a later attack version, opening the link triggers it automatically), and the attack code runs with the same permissions as the ChatGPT site, can call logged-in APIs to list recent conversations, open private chats that were never shared, and send the contents to a server controlled by the researchers. The vulnerability stems from three overlapping design issues, among which a listener left on the main page by the MathLive math library does not verify the message origin and allows raw HTML to be carried, enabling code inside the Preview sandbox to create a frame that inherits the chatgpt.com identity, and then execute code via a CSP-allowed YouTube script.
Related discussion
- X@TechsenseDev · TechSense DevelopersOne click on a shared link was enough. Parameter Labs showed a public ChatGPT share could run attacker JavaScript in a…(opens the original post in a new tab)
- WebAI Threat Watch (aithreat.io)Общая ссылка в ChatGPT открывала личные чаты, OpenAI закрыла баг(opens the original post in a new tab)
- WebAI Threat Watch (aithreat.io)ChatGPT, un lien partagé ouvrait les conversations privées, OpenAI corrige la faille(opens the original post in a new tab)
- X@openwikipedia · OpenWikiZero-Click Execution: Later versions of this exploit automated the process. Simply opening the link was enough. It cata…(opens the original post in a new tab)
3 likes·Nov 3 11:41Collect
- X@The_Cyber_News · Cyber Security News‼ ChatGPT Flaw Allowed Attackers to Hijack Accounts and Steal Private Conversations With One Link Details: https://cy…(opens the original post in a new tab)
139 likes · 6 comments·Nov 3 11:41Collect
- X@djcroman · djcromanA shared ChatGPT link could run attacker code in your session and read your private chats. Parameter Labs reported it…(opens the original post in a new tab)
- X@PandaAgents · PandAI🚨 ChatGPT had a hole. Your private chats could leak with one click. OpenAI confirmed it and rated it the most serious t…(opens the original post in a new tab)
26 likes · 7 comments·Nov 3 11:41Collect
- X@TimCohn · Tim Cohnhttps://thehackernews.com/2026/10/a-shared-chatgpt-link-could-run.html(opens the original post in a new tab)
- X@theadvtech · NexaTech📡 Signal: A crafted ChatGPT share link could execute attacker code in the signed-in session of anyone who opened it, re…(opens the original post in a new tab)
- X@spinidg · SPIN IDGOpenAI fixes a ChatGPT vulnerability that could expose private conversations through shared links. Researchers at Param…(opens the original post in a new tab)
- X@eggbaby · Eggb4byWhat's buzzing ### ChatGPT HTML preview share-link takeover disclosed Parameter Labs detailed a fixed ChatGPT account…(opens the original post in a new tab)
- WebAI Threat Watch (aithreat.io)Researchers Discover High-Severity ChatGPT Flaw That Exposed Private Conversations to Attackers(opens the original post in a new tab)
Attention trend
New sources per day
- Oct 31: 36 new sources (3 outlets, 33 accounts)
- Nov 1: 5 new sources (0 outlets, 5 accounts)
- Nov 2: 4 new sources (1 outlets, 3 accounts)
- Nov 3: 7 new sources (1 outlets, 6 accounts)