0-Click ChatGPT Agent Vulnerability Allows Sensitive Data Exfiltration from Gmail
A zero-click vulnerability discovered in ChatGPT’s Deep Research agent allowed attackers to exfiltrate sensitive data from a user’s Gmail account without any user interaction. The flaw, which OpenAI has since patched, leveraged a sophisticated form of indirect prompt injection hidden within an email, tricking the agent into leaking personal information directly from OpenAI’s cloud infrastructure. […]
The post 0-Click ChatGPT Agent Vulnerability Allows Sensitive Data Exfiltration from Gmail appeared first on Cyber Security News.