CVE-2023-37274 | Date: (C)2023-07-15 (M)2023-11-10 |
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.
CVSS Score and Metrics +CVSS Score and Metrics -CVSS V3 Severity: | CVSS V2 Severity: |
CVSS Score : 7.8 | CVSS Score : |
Exploit Score: 1.8 | Exploit Score: |
Impact Score: 5.9 | Impact Score: |
|
CVSS V3 Metrics: | CVSS V2 Metrics: |
Attack Vector: LOCAL | Access Vector: |
Attack Complexity: LOW | Access Complexity: |
Privileges Required: LOW | Authentication: |
User Interaction: NONE | Confidentiality: |
Scope: UNCHANGED | Integrity: |
Confidentiality: HIGH | Availability: |
Integrity: HIGH | |
Availability: HIGH | |
| |