CVE-2023-37275

System logs spoofable in Auto-GPT via ANSI control sequences

Description

Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. The Auto-GPT command line UI makes heavy use of color-coded print statements to signify different types of system messages to the user, including messages that are crucial for the user to review and control which commands should be executed. Before v0.4.3, it was possible for a malicious external resource (such as a website browsed by Auto-GPT) to cause misleading messages to be printed to the console by getting the LLM to regurgitate JSON encoded ANSI escape sequences (`\u001b[`). These escape sequences were JSON decoded and printed to the console as part of the model's "thinking process". The issue has been patched in release version 0.4.3.

Category

3.1
CVSS
Severity: Low
CVSS 3.1 •
EPSS 0.06%
Third-Party Advisory github.com Third-Party Advisory github.com
Affected: Significant-Gravitas Auto-GPT
Published at:
Updated at:

References

Link Tags
https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-r7f7-qrrv-3fjh third party advisory patch
https://github.com/Significant-Gravitas/Auto-GPT/pull/4810 third party advisory patch

Frequently Asked Questions

What is the severity of CVE-2023-37275?
CVE-2023-37275 has been scored as a low severity vulnerability.
How to fix CVE-2023-37275?
To fix CVE-2023-37275, make sure you are using an up-to-date version of the affected component(s) by checking the vendor release notes. As for now, there are no other specific guidelines available.
Is CVE-2023-37275 being actively exploited in the wild?
As for now, there are no information to confirm that CVE-2023-37275 is being actively exploited. According to its EPSS score, there is a ~0% probability that this vulnerability will be exploited by malicious actors in the next 30 days.
What software or system is affected by CVE-2023-37275?
CVE-2023-37275 affects Significant-Gravitas Auto-GPT.
This platform uses data from the NIST NVD, MITRE CVE, MITRE CWE, First.org and CISA KEV but is not endorsed or certified by these entities. CVE is a registred trademark of the MITRE Corporation and the authoritative source of CVE content is MITRE's CVE web site. CWE is a registred trademark of the MITRE Corporation and the authoritative source of CWE content is MITRE's CWE web site.
© 2025 Under My Watch. All Rights Reserved.