CVE-2023-37274Python code execution sandbox escape in non-docker version in Auto-GPT
- 7.6HighCVSS base score
- 0.35%Exploitation in 30 daysEPSS · top 71% of all CVEs
- NoKnown exploitednot in CISA's KEV catalog
- NonePublic exploitsnone known yet
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.
Timeline
ID reserved
By GitHub_M
- 14 days later
· 14 days later
Published
- 16 months later
· 16 months later
Record updated
Changes after publication (a new score, a public exploit, EPSS crossing 1, 10 or 50 %, leaving KEV) are kept since November 2026; earlier ones are not known.
Scores
| Scored by | CVSS | Score | Vector |
|---|---|---|---|
| GitHub_MCNA (assigner) | 3.1 | High7.6 | CVSS:3.1/AV:L/AC:H/PR:L/UI:R/S:C/C:H/I:H/A:H |
| NVDNVD · Analyzed | 3.1 | High7.8 | CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H |
- EPSS (exploitation in 30 days)
- 0.35% · top 71% of all CVEs (15 Nov 2026)
- CISA SSVC
- Exploitation: none · Automatable: no · Technical impact: total
The list uses the assigner's score when there is one, then CISA's, then NVD's: High 7.6.
Affected products
Significant-Gravitas · Auto-GPT
- affected < 0.4.3
References
References2
- https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-5h38-mgp9-rj5f (opens in a new tab)x_refsource_CONFIRMx_transferred
- https://github.com/Significant-Gravitas/Auto-GPT/pull/4756 (opens in a new tab)x_refsource_MISCx_transferred
Sources
The same CVE in the primary databases and aggregators, to check against.
- CVE.org record (opens in a new tab)
- CVE List JSON (GitHub) (opens in a new tab)
- NVD (opens in a new tab)
- FIRST EPSS (opens in a new tab)
- EUVD EUVD-2023-41185 (opens in a new tab)
- OSV.dev (opens in a new tab)
- GitHub Advisories (opens in a new tab)
- CIRCL Vulnerability-Lookup (opens in a new tab)
Badge for a README or a ticket
[](https://cveledger.app/cve/CVE-2023-37274)Record last updated .