dbcve.org
Autogpt ClassicApplication · Agpt

CVE-2023-37274

HIGH · 7.8 CVSS v3.1 Published 2023-07-13
Fix available
A fix is available. Upgrade to 0.4.3 or later.
See remediation →
80/100
Remediation priority · High
Zero-click Patch available

Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.

NVD · unedited
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.

Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.

dbcve analysis
How this class of weakness works · CWE-94

The application evaluates attacker-influenced input as code, handing them a way to run logic inside the process. Depending on the runtime this can escalate directly to remote code execution. Remediation means removing dynamic evaluation of untrusted input and replacing it with safe, data-driven alternatives.

General guidance for the code injection class — the official description and references above are authoritative for this specific CVE. Want a bespoke review and a reviewed fix? Ask our team →

Affected products & versions What the vendor confirmedThe version ranges the vendor confirmed as vulnerable. If your version sits inside a range here, treat yourself as exposed until you have upgraded.

NVD · CPE data
Autogpt ClassicApplication
Affected:< 0.4.3

CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.

From the vector
Attack vector
Local
Complexity
Low
Privileges
Low
User interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High

CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.

dbcve · scoped
Upgrade available Upgrade to 0.4.3 or later
Fixed in 0.4.3
Vendor patch github.com →
Recommended fix High confidence

0.4.3

  1. Back up any custom configurations, plugins, or data in your Auto-GPT installation
  2. Ensure you are currently running a version of Auto-GPT Classic below 0.4.3
  3. Update Auto-GPT to version 0.4.3 or later by pulling the latest code from the repository or downloading the release
  4. After updating, verify the execute_python_code command now properly sanitizes the basename argument
  5. Test that code execution is properly contained within the workspace directory
  6. If using run.sh or run.bat, ensure the docker container is properly configured to sandbox code execution

Generated from the published advisory — verify against the referenced sources before acting.

We can perform the upgrade in your staging environment and verify nothing breaks — typical engagement from $3,200. Get the upgrade done

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2023-37274 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.

Get it on GitHub Scan in the browser

References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.

Primary sources

Practitioner notes

Contributed

Peer-ranked notes from engineers who’ve handled CVE-2023-37274 in production — separate from our analysis above.

No notes yet

Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.

What this is

A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.

What belongs here
  • Verified mitigations, workarounds, and config changes
  • Version or environment caveats, and links to real fixes
  • No weaponised exploit code, or anything meant to cause harm
  • No spam, self-promotion, credentials, or personal data