Join us
Auto-GPT arbitrary code execution and docker escape: Researchers discovered a vulnerability in Auto-GPT that allowed attackers to execute arbitrary code by injecting prompts and manipulating the user approval process. They also found a method to escape the Auto-GPT docker image and gain access to the host system. These vulnerabilities were addressed in version 0.4.3.
Share with your friends and followers
Join other developers and claim your FAUN account now!
Only registered users can post comments. Please, login or signup.