Every CVE Search/ Get API key

CVE-2023-37273

Docker escape in Auto-GPT when running from docker-compose.yml included in git repo

8.1 HighPublic exploit

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.

Attack profile

How easy it is to exploit

Attack vector
Local
Complexity
Low
Privileges needed
Low
User interaction
Required

What an attacker can affect

Confidentiality
High
Integrity
High
Availability
Low

Exploit likelihood

0.36%Up 0.3 points since Jul 14, 2023
90%50%10%1%

What each source reports

CVE List Score used 8.1

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 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.

Record
CVE-2023-37273
CVSS 3.1
8.1 HighCVSS:3.1/AV:L/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:L
Weakness
CWE-94
Updated
2026-11-02
EUVDEUVD-2023-41184 8.1

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.

Record
EUVD-2023-41184
CVSS 3.1
8.1 HighCVSS:3.1/AV:L/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:L
Updated
2026-11-03
NVD 8.1

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.

Record
CVE-2023-37273
CVSS 3.1
8.1 HighCVSS:3.1/AV:L/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:L
CVSS 3.1
8.8 HighCVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
Weakness
CWE-94
Updated
2026-11-02
OSV 8.1

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 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.

Record
CVE-2023-37273
CVSS 3.1
8.1 HighCVSS:3.1/AV:L/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:L
Weakness
CWE-94
Updated
2026-11-02

Affected products

Public exploits

Links only. Every CVE stores no exploit code.

Public exploits
SourceLinkDate
PoC in GitHubgdesantis01/instructions-summarizing2025-06-23

History

History
RecordedChangedSources
aliases, publishedEUVD
first indexedCVE List, NVD, OSV, PoC in GitHub

Dates are when Every CVE recorded each change. Upstream dates may differ.

In short

CVE-2023-37273 is a high vulnerability (CVSS 8.1) in Significant-gravitas Auto-gpt, published July 13, 2023. Public exploit code exists. EPSS puts the chance of exploitation in the next 30 days at 0.36%, the 29th percentile. No source names a fixed version.

References

MoveEnter Open