Virtual Event: Threat Detection and Incident Response Summit - Watch Sessions
Connect with us

Hi, what are you looking for?



OpenAI Patches Account Takeover Vulnerabilities in ChatGPT

OpenAI resolved severe ChatGPT vulnerabilities that could have been exploited to take over accounts.

Last week, ChatGPT creator OpenAI patched multiple severe vulnerabilities that could have allowed attackers to take over user accounts and view chat histories.

The first was a critical web cache deception bug that could have allowed attackers to access user information such as names, emails, and access tokens, which OpenAI’s API would fetch from the server.

To exploit the vulnerability, an attacker could craft a .css path to the session endpoint and send the link to the victim. When the victim opens the link, the response is cached and the attacker can harvest the victim’s credentials and take over their account.

Reported by Shockwave CEO and founder Gal Nagli, the bug was quickly addressed by instructing “the caching server to not catch the endpoint through a regex”.

The fix, however, was not enough to keep an attacker out of user accounts, security researcher and CISO Ayoub Fathi explains. While analyzing the fix, he discovered a bypass method that could be used against another ChatGPT API, providing an attacker with access to a user’s conversation titles.

This was basically another web cache deception attack: the API response to a forged ‘/backend-api/conversations’ link would be cached, revealing the victim’s HTTP response, which contains the conversations’ titles.

Digging deeper, the researcher was able to bypass OpenAI’s fix for the original account takeover issue, using a new payload, and discovered that all ChatGPT APIs were vulnerable to the bypass, allowing an attacker to read conversation titles, full chats, and account status.

Advertisement. Scroll to continue reading.

Fathi says he worked with the OpenAI team to help them fully address all issues.

No bug bounty reward was issued to either researcher, as OpenAI does not have a bug bounty program in place.

The vulnerabilities were reported days after OpenAI took ChatGPT offline to address a vulnerability in an open-source Redis client library, which allowed users to view other users’ chat data and payment-related information.

Related: ChatGPT Data Breach Confirmed as Security Firm Warns of Vulnerable Component Exploitation

Related: Microsoft Puts ChatGPT to Work on Automating Cybersecurity

Related: ChatGPT and the Growing Threat of Bring Your Own AI to the SOC

Written By

Ionut Arghire is an international correspondent for SecurityWeek.

Click to comment

Daily Briefing Newsletter

Subscribe to the SecurityWeek Email Briefing to stay informed on the latest threats, trends, and technology, along with insightful columns from industry experts.

SecurityWeek’s Threat Detection and Incident Response Summit brings together security practitioners from around the world to share war stories on breaches, APT attacks and threat intelligence.


Securityweek’s CISO Forum will address issues and challenges that are top of mind for today’s security leaders and what the future looks like as chief defenders of the enterprise.


Expert Insights

Related Content


Less than a week after announcing that it would suspended service indefinitely due to a conflict with an (at the time) unnamed security researcher...

Data Breaches

OpenAI has confirmed a ChatGPT data breach on the same day a security firm reported seeing the use of a component affected by an...

Risk Management

The supply chain threat is directly linked to attack surface management, but the supply chain must be known and understood before it can be...


The latest Chrome update brings patches for eight vulnerabilities, including seven reported by external researchers.


Patch Tuesday: Microsoft warns vulnerability (CVE-2023-23397) could lead to exploitation before an email is viewed in the Preview Pane.


Apple has released updates for macOS, iOS and Safari and they all include a WebKit patch for a zero-day vulnerability tracked as CVE-2023-23529.

IoT Security

A group of seven security researchers have discovered numerous vulnerabilities in vehicles from 16 car makers, including bugs that allowed them to control car...

Application Security

Drupal released updates that resolve four vulnerabilities in Drupal core and three plugins.