OpenAI Patches ChatGPT Gmail Flaw Exploited by Hackers in Deep Research Attacks

OpenAI has fixed a security vulnerability that could have allowed hackers to manipulate ChatGPT into leaking sensitive data from a victim’s Gmail inbox. The flaw, uncovered by cybersecurity company Radware and reported by Bloomberg, involved ChatGPT’s “deep research” feature. This function enables the AI to carry out advanced tasks such as web browsing and analyzing files or emails stored in services like Gmail, Google Drive, and Microsoft OneDrive. While useful, the tool also created a potential entry point for attackers to exploit.  

Radware discovered that if a user requested ChatGPT to perform a deep research task on their Gmail inbox, hackers could trigger the AI into executing malicious instructions hidden inside a carefully designed email. These hidden commands could manipulate the chatbot into scanning private messages, extracting information such as names or email addresses, and sending it to a hacker-controlled server. The vulnerability worked by embedding secret instructions within an email disguised as a legitimate message, such as one about human resources processes. 

The proof-of-concept attack was challenging to develop, requiring a detailed phishing email crafted specifically to bypass safeguards. However, if triggered under the right conditions, the vulnerability acted like a digital landmine. Once ChatGPT began analyzing the inbox, it would unknowingly carry out the malicious code and exfiltrate data “without user confirmation and without rendering anything in the user inte

[…]
Content was cut in order to protect the source.Please visit the source for the rest of the article.