Skip to content
Fencer Vulns
high 7.6

CVE-2023-37274 json

Python code execution sandbox escape in non-docker version in Auto-GPT

published 2023-07-13 3 y ago modified 2026-06-17 4 mo ago also EUVD-2023-41185

cvss
7.6
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.4%
EPSS 0.4% chance of exploitation in 30 days, percentile 29%
public exploits
0
none known

Summary

Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. When Auto-GPT is executed directly on the host system via the provided run.sh or run.bat files, custom Python code execution is sandboxed using a temporary dedicated docker container which should not have access to any files outside of the Auto-GPT workspace directory. Before v0.4.3, the `execute_python_code` command (introduced in v0.4.1) does not sanitize the `basename` arg before writing LLM-supplied code to a file with an LLM-supplied name. This allows for a path traversal attack that can overwrite any .py file outside the workspace directory by specifying a `basename` such as `../../../main.py`. This can further be abused to achieve arbitrary code execution on the host running Auto-GPT by e.g. overwriting autogpt/main.py which will be executed outside of the docker environment meant to sandbox custom python code execution the next time Auto-GPT is started. The issue has been patched in version 0.4.3. As a workaround, the risk introduced by this vulnerability can be remediated by running Auto-GPT in a virtual machine, or another environment in which damage to files or corruption of the program is not a critical problem.

Patch / fix

  • agpt autogpt_classic 0.4.3

CISA SSVC

Exploitation
none
Automatable
no
Technical impact
total
Assessed
2 y ago

Exploit prediction

0.35% chance of exploitation in the next 30 days, higher than 29% of all scored CVEs (FIRST EPSS, 2026-11-08).

CVSS scores

assigned by version score vector
CNA 3.1 7.6 CVSS:3.1/AV:L/AC:H/PR:L/UI:R/S:C/C:H/I:H/A:H
NVD 3.1 7.8 CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

Affected products

  • Significant-Gravitas Auto-GPT

Classification

Weakness
  • CWE-94 Improper Control of Generation of Code

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.