CVE & CISA-KEV Catalog

CVE-2023-37275

LOW
3.1
CVSS v3
NVD

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.

How to fix

Remediation Available
auto-gptNVD
Affected:< 0.4.3Fixed in:0.4.3CVE-2023-37275derived from NVD
autogpt classicNVD
Affected:< 0.4.3Fixed in:0.4.3CVE-2023-37275derived from NVD

TridentStack Control can deploy fixes like this automatically across your Windows, macOS, and Linux fleet. See how it works

Remediation is compiled from vendor and distribution security advisories. Always confirm against the linked source for your exact version and platform.

CVSS v3 Vector

Exploitability

Attack VectorNetwork
Attack ComplexityHigh
Privileges RequiredNone
User InteractionRequired
ScopeUnchanged

Impact

ConfidentialityNone
IntegrityLow
AvailabilityNone

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

Exploit Intelligence

0.44%probability of exploitation in 30 days
36thpercentile

Low risk: more likely to be exploited than 36% of all known CVEs.

References

Related Vulnerabilities

Other CWE-117 vulnerabilities, ordered by exploit likelihood. View all

CVESeverityCVSSEPSSExploitedFix
CVE-2021-43410Medium5.32.4%-Fix
CVE-2022-32549Medium5.32.3%--
CVE-2019-14864Medium6.51.9%-Fix
CVE-2021-42250Medium6.51.8%-Fix
CVE-2024-47083High7.51.6%--
CVE-2020-25646High7.51.4%--

Common questions

How do I fix CVE-2023-37275?

Published advisories record a fix for 2 affected products. The "How to fix" section on this page lists the fixed version and source advisory for each one, so apply the entry matching what you actually run.

Is CVE-2023-37275 being actively exploited?

Not that we know of. CVE-2023-37275 is not in the CISA Known Exploited Vulnerabilities catalog. Its EPSS score of 0.44% is the estimated probability that it will be exploited in the next 30 days. That is higher than 36% of all scored CVEs.

How severe is CVE-2023-37275?

CVE-2023-37275 has a CVSS v3 base score of 3.1, rated low. CVSS rates the technical impact if the vulnerability is exploited, not how likely that is, so weigh it alongside the exploit-prediction score when you decide what to patch first.

What does CVE-2023-37275 affect?

Published advisories record a fix for auto-gpt (NVD), autogpt classic (NVD). Only products with a sourced advisory are listed, so treat this as what we can cite rather than a complete inventory.

Embed a live status badge for CVE-2023-37275
CVE-2023-37275 severity badge

Markdown

[![CVE-2023-37275](https://tridentstack.com/cve/badge/CVE-2023-37275.svg)](https://tridentstack.com/cve/CVE-2023-37275)

HTML

<a href="https://tridentstack.com/cve/CVE-2023-37275"><img src="https://tridentstack.com/cve/badge/CVE-2023-37275.svg" alt="CVE-2023-37275"></a>

Find and fix vulnerabilities across your fleet

TridentStack Control continuously scans your Windows, macOS, and Linux fleet for known vulnerabilities, prioritizes them by severity and active exploitation, and patches them automatically.

See how it worksStart freeThis CVE lookup is free and always will be.

This product uses NVD data but is not endorsed or certified by the NVD. EPSS scores courtesy of FIRST.org (https://www.first.org/epss). Source: CISA KEV Catalog. Data as of 2026-02-24.