CVE-2023-37273 Docker escape in Auto-GPT when running from docker-compose.yml included in git repo
Attackers can execute arbitrary code to overwrite configuration files, enabling container escape and host system compromise in Auto-GPT.
- Exploited in the wild
- Not known
- Login needed
- Any signed-in user
- Attackable
- Local or same network only
- Victim action needed
- A user has to click or open something
- Fix
- None listed
What is CVE-2023-37273?
CVE-2023-37273 is a high-severity code injection vulnerability in Significant-Gravitas Auto-GPT, published on 13 Jul 2023. It can only be exploited from the same machine or local network, and only if a user opens a file or follows a link.
Official 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.
Weakness: CWE-94
Which versions are affected by CVE-2023-37273?
It affects 1 product.
Products include Agpt Autogpt Classic.
How do I fix CVE-2023-37273?
No fix has been published for CVE-2023-37273 yet. Limit exposure of the affected software until one is available.
Upgrade, and never evaluate templates, expressions or code built from user input. More about Code injection.
Is CVE-2023-37273 being exploited?
There is no known exploitation of CVE-2023-37273 in the wild and no public exploit code.
Public exploit code: 1 proofs of concept on GitHub.
Other vulnerabilities in Significant-Gravitas Auto-GPT
- CVE-2024-6091 Shell Command Denylist Bypass in significant-gravitas/autogpt
- CVE-2024-8156 Command Injection in significant-gravitas/autogpt
- CVE-2024-1879 CSRF to RCE in significant-gravitas/autogpt
- CVE-2024-1881 Improper Neutralization of Special Elements used in an OS Command in significant-gravitas/autogpt
- CVE-2024-1880 OS Command Injection in MacOS Text-To-Speech Class in significant-gravitas/autogpt
Sources
Also known as GHSA-x5gj-2chr-4ch6.