#chatgpt-security

[ follow ]
Information security
fromSecurityWeek
1 week ago

Chrome, Edge Extensions Caught Stealing ChatGPT Sessions

Malicious browser extensions stole ChatGPT session tokens by injecting content scripts into chatgpt.com, exfiltrating authorization headers and user data to remote servers.
Information security
fromIT Pro
3 months ago

Cyber researchers have already identified several big security vulnerabilities on OpenAI's Atlas browser

OpenAI's Atlas browser contains vulnerabilities enabling attackers to inject malicious instructions into ChatGPT memory, enabling remote code execution, persistent compromise, and increased phishing risk.
[ Load more ]