Auto-GPT: Improper Control of Generation of Code
CVE-2023-37274 is a high-severity improper control of generation of code vulnerability in Auto-GPT from Significant-Gravitas, with a CVSS 3.1 base score of 7.8 out of 10. It can be exploited with local access to the system by an attacker with a low-privileged account, without any action from a user. Affected Auto-GPT versions: < 0.4.3. The record does not name a fixed version, so check the vendor advisory. There is no confirmed exploitation so far. EPSS estimates a 0.35% chance of exploitation within 30 days, which is low compared with other CVEs.
High severity with no evidence of exploitation so far.
What to do
- Update Autogpt Classic to 0.4.3 or a later version.
- Read the advisory on github.com for workarounds and exact fixed builds.
Affected products and versions
| Vendor | Product | Affected versions | Fixed in |
|---|---|---|---|
| Significant-Gravitas | Auto-GPT | < 0.4.3 | Not stated |
| Agpt | Autogpt Classic | before 0.4.3 | 0.4.3 |
Version data comes from the organisation that assigned the CVE. Confirm against the vendor advisory before deciding you are unaffected.
How the severity score breaks down
- Attack vector
- LocalThe attacker needs local access or must trick a user into running something.
- Attack complexity
- LowNo special conditions are needed; the attack works reliably.
- Privileges required
- LowA basic user account is enough.
- User interaction
- NoneNo action by a victim is required.
- Scope
- UnchangedImpact stays within the vulnerable component.
- Confidentiality
- HighAll data handled by the component can be read.
- Integrity
- HighData or code can be modified at will.
- Availability
- HighThe component can be taken down completely.
Vector: CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H. Scored by NVD.
| Scoring system | Score | Severity | Scored by |
|---|---|---|---|
| CVSS 3.1 | 7.5 | High | CNA (github.com) |
| CVSS 3.1 | 7.8 | High | NVD |
Official 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.
Source: the CVE record as published by its numbering authority, via NVD and CVE.org.
The underlying weakness: Improper Control of Generation of Code
The product constructs all or part of a code segment using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the syntax or behavior of the intended code segment.
How developers prevent this class of flaw
- Refactor your program so that you do not have to dynamically generate code.
- Run your code in a jail or similar sandbox environment that enforces strict boundaries between the process and the operating system. This may effectively restrict which code can be executed by your product. Examples include the Unix chroot jail and AppArmor. In general, managed code may provide some protection. This may not be a feasible solution, and it only limits the impact to the operating system; the rest of your application may still be subject to compromise. Be careful to avoid CWE-243 and other weaknesses related to jails.
- Use dynamic tools and techniques that interact with the product using large test suites with many diverse inputs, such as fuzz testing (fuzzing), robustness testing, and fault injection. The product's operation may slow down, but it should not become unstable, crash, or generate incorrect results.
More Improper Control of Generation of Code vulnerabilities (CWE-94)
Timeline
- CVE record published.
- CISA published its SSVC assessment (exploitation: none, automatable: no, technical impact: total).
- Record last changed materially (score, affected products, status or references).
References
Advisories
- github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-5h38-mgp9-rj5fThird Party Advisory
Patches and release notes
- github.com/Significant-Gravitas/Auto-GPT/pull/4756Third Party Advisory
Other vulnerabilities in Auto-GPT
- 8.8 High severity
Recent Improper Control of Generation of Code vulnerabilities
- 8.0 High severity
- 9.8 Critical severity
- 7.2 High severity
- 7.2 High severity
- 8.8 High severity
- 8.8 High severity
Spotted an error? Tell us.