CVE-2023-37273: Docker escape in Auto-GPT when running from docker-compose.yml included in git repo
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 executepythonfile and executepythoncode 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.
Affected Software
Remediation
Recommended actions to resolve this vulnerability, in priority order.
- Upgrade
Upgrade
Auto-GPTto a version that resolves this vulnerability.Fixed in 0.4.3 - Operational
If Auto-GPT was run using an unpatched version prior to 0.4.3, inspect and restore the repo-root docker-compose.yml to the expected, unmodified contents before restarting Auto-GPT.
Event History
Frequently Asked Questions
What is the severity of CVE-2023-37273?
CVE-2023-37273 is classified as a moderate severity vulnerability affecting Auto-GPT versions prior to 0.4.3.
How do I fix CVE-2023-37273?
To fix CVE-2023-37273, upgrade Auto-GPT to version 0.4.3 or later.
What does CVE-2023-37273 affect?
CVE-2023-37273 affects the Auto-GPT application when using versions before 0.4.3.
What is Auto-GPT?
Auto-GPT is an experimental open-source application that demonstrates the capabilities of the GPT-4 language model.
Is CVE-2023-37273 a critical vulnerability?
No, CVE-2023-37273 is not classified as critical but should still be addressed promptly to maintain security.