CVE-2023-37274
CVE-2023-37274 is a high-severity vulnerability in Agpt Autogpt Classic with a CVSS 3.x base score of 7.5. It is not currently listed as actively exploited by CISA, and its EPSS exploit-prediction score is low. The underlying weakness is classified as CWE-94.
Key facts
- Severity: High (CVSS 3.x base score 7.5)
- EPSS exploit prediction: 0% (26th percentile)
- Actively exploited: Not listed in CISA KEV
- Weakness: CWE-94
- Affected product: Agpt Autogpt Classic
- Published:
- Last modified:
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.
Frequently asked questions
- What is 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.
- How severe is CVE-2023-37274?
- CVE-2023-37274 has a CVSS 3.x base score of 7.5, rated high severity. It is exploitable over local access with high attack complexity, requires low privileges and user interaction. Impact on confidentiality is high, integrity high, and availability high.
- Is CVE-2023-37274 being actively exploited?
- It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 0% (26th percentile), an estimate of the probability of exploitation in the next 30 days.
- What products are affected by CVE-2023-37274?
- CVE-2023-37274 affects Agpt Autogpt Classic. See the affected-products list for the exact vulnerable versions.
- How do I fix CVE-2023-37274?
- Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround. Given its high severity, prioritise patching exposed systems.
- When was CVE-2023-37274 published?
- CVE-2023-37274 was published on 2023-07-13 and last updated on 2026-06-17.
References
- https://github.com/Significant-Gravitas/Auto-GPT/pull/4756
- https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-5h38-mgp9-rj5f
Affected products (1)
- cpe:2.3:a:agpt:autogpt_classic:*:*:*:*:*:*:*:*
More vulnerabilities in Agpt Autogpt Classic
- CVE-2024-8156 — Critical (CVSS 9.8): A command injection vulnerability exists in the workflow-checker.yml workflow of significant-gravitas/autogpt. The…
- CVE-2024-6091 — Critical (CVSS 9.8): A vulnerability in significant-gravitas/autogpt version 0.5.1 allows an attacker to bypass the shell commands denylist…
- CVE-2024-1881 — Critical (CVSS 9.8): AutoGPT, a component of significant-gravitas/autogpt, is vulnerable to an improper neutralization of special elements…
- CVE-2024-1879 — High (CVSS 8.8): A Cross-Site Request Forgery (CSRF) vulnerability in significant-gravitas/autogpt version v0.5.0 allows attackers to…
- CVE-2023-37273 — High (CVSS 8.1): Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. Running…
- CVE-2024-1880 — High (CVSS 7.8): An OS command injection vulnerability exists in the MacOS Text-To-Speech class MacOSTTS of the…
All CVEs affecting Agpt Autogpt Classic →
Other CWE-94 (Code Injection) vulnerabilities
- CVE-2026-57624 — Critical (CVSS 10.0): Unauthenticated Remote Code Execution (RCE) in Blocksy Companion Pro <= 2.1.46 versions.
- CVE-2026-10134 — Critical (CVSS 10.0): IBM Langflow OSS 1.0.0 through 1.9.3 allows an attacker to read every secret available to the Langflow process, read…
- CVE-2026-53576 — Critical (CVSS 10.0): Kestra is an open-source, event-driven orchestration platform. Prior to 1.0.45 and 1.3.21, the authentication filter…
- CVE-2026-10561 — Critical (CVSS 10.0): IBM Langflow OSS 1.0.0 through 1.9.3 has an vulnerability due to an improper isolation of Python execution combined…
- CVE-2026-25470 — Critical (CVSS 10.0): Improper Control of Generation of Code ('Code Injection') vulnerability in ACPT ACPT (Pro) - Custom Post Types Plugin…
- CVE-2026-48836 — Critical (CVSS 10.0): Unauthenticated Remote Code Execution (RCE) in Easy Invoice <= 2.1.19 versions.