OpenAI patched a ChatGPT security flaw that could have allowed hackers to extract Gmail data from its users, according to researchers at cyber firm Radware.<\/p>\n\n\n\n
The issue was found in ChatGPT\u2019s Deep Research agent,\u00a0a tool launched in February\u00a0to help users analyse large troves of information. <\/p>\n\n\n\n
The vulnerability\u00a0could have enabled attackers to siphon sensitive data from corporate or personal Gmail accounts, according to the findings. <\/p>\n\n\n\n
ChatGPT users who linked their Gmail accounts to the service may have unknowingly exposed their data to hackers, Radware researchers said.<\/p>\n\n\n\n
The Deep Research tool from OpenAI is designed to more comprehensively\u00a0conduct online research on users\u2019 behalf\u00a0and\u00a0quickly answer\u00a0complex questions. <\/p>\n\n\n\n
It can also connect to users\u2019 Gmail accounts if they authorise it. <\/p>\n\n\n\n
Deep Research is available to ChatGPT users who pay an extra fee and marks an expansion of the company\u2019s AI agents, or tools designed to carry out tasks with limited human intervention<\/p>\n\n\n\n
Radware uncovered the vulnerability, and researchers said there was no evidence that attackers had exploited it.\u00a0OpenAI told Radware it fixed the flaw on 3 September.\u00a0<\/p>\n\n\n\n
An OpenAI spokesperson said the safety of its models was important to the company, and it is continually improving standards to make its technology more robust against such exploits. <\/p>\n\n\n\n
\u201cResearchers often test these systems in adversarial ways, and we welcome their research as it helps us improve,\u201d the spokesperson said. <\/p>\n\n\n\n