RCE in Agpt Autogpt Classic
CVE-2023-37274
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.
Vulnerability class: RCE (Remote Code Execution)
Published · last modified .
CVSS v3 metric
CVSS v3 base score 7.5 (High). Vector: CVSS:3.1/AV:L/AC:H/PR:L/UI:R/S:C/C:H/I:H/A:H.
EPSS exploit prediction
EPSS: 0.004 (26.3th percentile), scored .
Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 26th percentile — 26.3% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.
EPSS over last 30 days · oldest: 0.004 · newest: 0.004 · change: 0.000
Affected products
- Agpt Autogpt Classic
- Significant-Gravitas Auto-Gpt — versions < 0.4.3
Weakness classification (CWE)
Public proof-of-concept exploits
References
- github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-5h38-mgp9-rj5f (Patch, Third Party Advisory)
- github.com/Significant-Gravitas/Auto-GPT/pull/4756 (Patch, Third Party Advisory)
Frequently asked questions
- What is CVE-2023-37274?
- CVE-2023-37274 is a high-severity vulnerability in Agpt Autogpt Classic, classified under Code Injection. CVSS score: 7.5/10. Published 2023-07-13.
- How severe is CVE-2023-37274?
- High severity. CVSS v3 base score is 7.5 out of 10.
- Is CVE-2023-37274 known to be exploited?
- 1 public proof-of-concept repositories are indexed. Not currently listed in the CISA KEV catalog.