CVE-2023-37274
7.5 · HIGHOverview
CVE-2023-37274 is a high-severity vulnerability affecting agpt autogpt_classic. It was published on July 13, 2023 and has a CVSS 3.1 base score of 7.5 (HIGH).
This vulnerability has a CVSS 3.1 base score of 7.5, rated HIGH. It requires local or adjacent network access to exploit. Some level of privileges is required for exploitation.
Technical 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 bee
Remediation
Check the references section for vendor advisories and patches from agpt. Update autogpt_classic to the latest patched version. If immediate patching is not possible, review the CVSS vector to understand the attack surface and apply compensating controls such as network segmentation or access restrictions.
Affected Products
| Vendor | Product | Versions | Status |
|---|---|---|---|
| agpt | autogpt_classic | >= 0, < 0.4.3 | Affected |
References
Frequently Asked Questions
What is CVE-2023-37274?
CVE-2023-37274 is a high-severity vulnerability affecting agpt autogpt_classic. It was published on July 13, 2023 and has a CVSS 3.1 base score of 7.5 (HIGH).
How severe is CVE-2023-37274?
This vulnerability has a CVSS 3.1 base score of 7.5, rated HIGH. It requires local or adjacent network access to exploit. Some level of privileges is required for exploitation.
How do I fix or remediate CVE-2023-37274?
Check the references section for vendor advisories and patches from agpt. Update autogpt_classic to the latest patched version. If immediate patching is not possible, review the CVSS vector to understand the attack surface and apply compensating controls such as network segmentation or access restrictions.
How can CyberStrike help with CVE-2023-37274?
CyberStrike's AI-powered security agents can automatically detect CVE-2023-37274 across your infrastructure using autonomous pentesting, DAST scanning, and HackBrowser. The platform continuously monitors for known vulnerabilities and provides actionable remediation guidance prioritized by real-world exploitability.
How CyberStrike Helps
AI agents map your attack surface to find vulnerabilities like this one.
Automated penetration testing that runs continuously, not just quarterly.
AI-driven PR review catches vulnerable dependencies before they ship.
Browser-based exploitation validates findings with real proof-of-concept.
Related HIGH CVEs from 2023
View all →support_uri parameter in the WARP client local settings file (mdm.xml) lacked proper validation whic
ZoneMinder is a free, open source Closed-circuit television software application for Linux which sup
ZoneMinder is a free, open source Closed-circuit television software application for Linux which sup
XWiki Platform is a generic wiki platform. Starting in version 12.10, a user without script rights c
XWiki Commons are technical libraries common to several other top level XWiki projects. The Livetab
XWiki Commons are technical libraries common to several other top level XWiki projects. A user witho
Session Validation attacks in Apache Superset versions up to and including 2.0.1. Installations that
Leantime is a lean open source project management system. Starting in version 2.3.21, an authenticat
IBM Security Guardium 11.3, 11.4, and 11.5 is vulnerable to stored cross-site scripting. This vulner
Thanks to the weaknesses that the web application has at the user management level, an attack
JumpServer is an open source bastion host. Logged-in users can access and modify the contents of any
lte-pic32-writer is a writer for PIC32 devices. In versions 0.0.1 and prior, those who use `sendto.t