The exploit chain stemmed from an unexpected interaction between ChatGPT's isolated HTML Preview feature and an interactive graphing tool. A browser messaging listener inside the third-party MathLive library failed to validate sender origins, enabling untrusted markup to breach the main document via an unsandboxed frame. This allowed malicious code to call authenticated APIs on behalf of the victim without requiring software installations or user interaction. OpenAI fully resolved the P1-classified security vulnerability on October 26.
Key points
The zero-interaction exploit bypassed both ChatGPT's content security policy and its isol…: The zero-interaction exploit bypassed both ChatGPT's content security policy and its isolated preview sandbox.
Complex feature combinations involving third-party libraries can expose major vulnerabili…: Complex feature combinations involving third-party libraries can expose major vulnerabilities within heavily protected web applications.
OpenAI patched the critical flaw after tracking the issue as a top-priority P1 security i…: OpenAI patched the critical flaw after tracking the issue as a top-priority P1 security incident.
Sources checked by our analysis pipeline: 1
Do the Math: How We Took Over ChatGPT Accounts
By bypassing ChatGPT's sandbox and content security policy, our research team was able to take over anyone's account simply by sending them a link.
In October 2026, we found a way to turn an ordinary public ChatGPT share into attacker-controlled JavaScript running inside the signed-in session of whoever opened it.
An attacker could create a malicious conversation, publish it using ChatGPT's normal sharing feature, and send the link to another user. When the victim opened the share, the payload executed as chatgpt.com
with access to the victim's authenticated web session.
We confirmed that this code could enumerate the victim's conversation list, retrieve content from a private conversation that had never been shared with the attacker, and send data from that conversation to an external server. The payload was not limited to modifying the page or displaying an alert—it could directly call ChatGPT's authenticated APIs as the victim, essentially allowing us to take over the victim's ChatGPT account.
The victim did not need to install an App, join a Project, paste code,…
The artificial intelligence firm disclosed an $80 billion net loss alongside extensive compute obligations in its initial prospectus filing. At the same time, major partners and backers are facing steep cash flow declines tied to massive infrastructure spending. These mounting financial pressures across the sector threaten to complicate investor confidence ahead of the company's upcoming roadshow.
Corporate leverage across the technology sector has reached dangerous levels as industry leaders face intense Wall Street scrutiny over capital allocation. Lawmakers are preemptively rejecting any public financial backstops should expensive investments in chips and compute infrastructure fail to deliver timely returns. This growing skepticism coincides with severe market turbulence that is actively wiping out trillions in equity value.
Technology giants are increasingly tying themselves to chipmakers, infrastructure providers, and startups through intricate leases, special-purpose vehicles, and residual-value guarantees. This interconnected web obscures liabilities just as capital expenditure accelerates. Should overall market demand stumble, these hidden balance-sheet exposures could amplify losses across the entire sector.