CVE-2023-37274

Home/CVE/Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. When Auto-G

CVE

Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. When Auto-G

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.

HIGH · CVSS 7.5 EPSS 0.0007

Act now

Public exploit or PoC is available
CVSS base score ≥ 7.0

Sigma rules0 YARA rules0

Look this up elsewhere - one-click external pivots

NVD CVE.org CISA Vulners Exploit-DB GitHub PoC VulnCheck KEV GreyNoise

▸ How to read a CVE - triage first, then detect and patch

This page is every public fact about CVE-2023-37274, cross-linked. Its job is to answer one question fast - does this need my attention now? - and then hand you the two things you do about it. Here is how an analyst reads it.

Triage: should I act now? Four signals, and they are not interchangeable:

CVSSseverity - how bad it is IF exploited, 0-10. A high CVSS alone is not urgency; a flaw can be a perfect 10 and never actually be attacked. EPSSprobability - a model’s estimate of the chance it is exploited in the next 30 days, 0-1. This is the “will it actually happen” signal. CISA KEVconfirmed - it is being exploited in the wild right now. The strongest signal on the page; KEV beats any score. Weaponisedavailability - public exploits / PoCs, and especially Metasploit modules rated Excellent / Great. Reliable, packaged exploit code means low-skill attackers can use it today.

How they combine: KEV, or a dependable Metasploit module, means patch now regardless of CVSS. High CVSS + low EPSS + no exploit is real but not an emergency - schedule it. Low CVSS but KEV-listed still gets patched now. The verdict above already weighed these for you; this is how it got there.

Then what - two workflows:

Detectwhen you cannot patch today, follow this CVE to the ATT&CK techniques it enables, then Build a SIEM detection (the green button) - author a rule, test it in Atomic, deploy it. That buys visibility while the patch waits. PatchAffected products / packages tell you if you are exposed; Fixed versions by distribution and Vendor advisories give the exact version that closes it.

Reading order for the panels below: verdict + badges, then Public exploits / Metasploit (is it weaponised), then ATT&CK techniques + Sigma / IDS rules (can I detect it), then Affected products / packages + Fixed versions (am I exposed, what patches it), then Threat actors / IOCs (who uses it), then Scoring & timeline / references (the evidence).

View attack path from CVE-2023-37274

◆

ATT&CK techniques

Techniques this CVE enables - linked via CWECAPECATT&CK. High◆ = named directly in ATT&CK or Nuclei templates.

T1027.006 · HTML Smuggling T1027.009 · Embedded Payloads T1564.009 · Resource Forking

▤ Build a SIEM detection for these techniques

▤

CAPEC attack patterns

Attack patterns this CVE enables - the bridge from weakness to ATT&CK technique.

CAPEC-CAPEC-242 · Code Injection CAPEC-CAPEC-35 · Leverage Executable Code in Non-Executable Files CAPEC-CAPEC-77 · Manipulating User-Controlled Variables

⬡

Weakness Classification

CWE-94Improper Control of Generation of Code ('Code Injection')

▤

Affected Products & Versions

agpt autogpt classic< 0.4.3

⚠

Public Exploits & PoCs

These PoC and exploit links come from public sources and are not verified to be safe or functional. Review the code before running anything, and treat unverified entries as untrusted.

pocfkie-cad/nvd-json-data-feeds (trickest)

▣

Scoring & Timeline

7.5

HIGH · CVSS v3.1 · [email protected]

View on NVD

Attack Vector

Network Adjacent Local Physical

Attack Complexity

Low High

Privileges Required

None Low High

User Interaction

None Required

Scope

Unchanged Changed

Confidentiality

None Low High

Integrity

None Low High

Availability

None Low High

Published to NVD13 Jul 2023 · 11:15 PM

CVSS VectorCVSS:3.1/AV:L/AC:H/PR:L/UI:R/S:C/C:H/I:H/A:H

SSVC triage · cisa-vulnrichment

Exploitation

none

Automatable

Technical impact

total

SSVC asks the questions that actually drive patch urgency: is it being exploited, can attacks be automated, and how total is the impact.

🔗

References & Sources

Source URLs (vendor pages, mailing lists, write-ups). Exploit/PoC links are in their own section above to avoid duplication.

https://github.com/Significant-Gravitas/Auto-GPT/pull/4756PatchThird Party Advisory

https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-5h38-mgp9-rj5fPatchThird Party Advisory