Security researchers found and reported a vulnerability in OpenAI's ChatGPT that could allow attackers to execute code within the authenticated sessions of users who opened a malicious share link. The bug was serious enough to affect anyone logged into ChatGPT who clicked the attacker's link.
OpenAI awarded the researchers a $5,000 bug bounty for the responsible disclosure. The company operates a vulnerability disclosure program to identify and patch security issues before they can be exploited at scale.
This is an AI-written summary. The original reporting belongs to Techmeme. How we write these · Spot a mistake?