cve/2023/CVE-2023-37273.md

### [CVE-2023-37273](https://cve.mitre.org/cgi-bin/cvename.cgi?name=CVE-2023-37273)
![](https://img.shields.io/static/v1?label=Product&message=Auto-GPT&color=blue)
![](https://img.shields.io/static/v1?label=Version&message=%3D%20%3C%200.4.3%20&color=brighgreen)
![](https://img.shields.io/static/v1?label=Vulnerability&message=CWE-94%3A%20Improper%20Control%20of%20Generation%20of%20Code%20('Code%20Injection')&color=brighgreen)

### Description

Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. Running Auto-GPT version prior to 0.4.3 by cloning the git repo and executing `docker compose run auto-gpt` in the repo root uses a different docker-compose.yml file from the one suggested in the official docker set up instructions. The docker-compose.yml file located in the repo root mounts itself into the docker container without write protection. This means that if malicious custom python code is executed via the `execute_python_file` and `execute_python_code` commands, it can overwrite the docker-compose.yml file and abuse it to gain control of the host system the next time Auto-GPT is started. The issue has been patched in version 0.4.3.

### POC

#### Reference
No PoCs from references.

#### Github
- https://github.com/fkie-cad/nvd-json-data-feeds