Hacking Auto-GPT and escaping its docker container

We leverage indirect prompt injection to trick Auto-GPT (GPT-4) into executing arbitrary code when it is asked to perform a seemingly harmless task such as text summarization on a malicious website, and discovered vulnerabilities that allow escaping its sandboxed execution environment.

auto auto-gpt code container docker environment gpt gpt-4 hacking injection malicious malicious website prompt injection task text vulnerabilities website