Is CVE-2023-37275 in the CISA KEV catalog?

No. CVE-2023-37275 is not currently on the CISA Known Exploited Vulnerabilities list.

What is the CVSS severity of CVE-2023-37275?

CVE-2023-37275 has a CVSS v3 base score of 3.1 (LOW).

What is the EPSS score for CVE-2023-37275?

CVE-2023-37275 has an EPSS score of 0.44% (35th percentile), estimating the probability of exploitation in the next 30 days.

How do I fix CVE-2023-37275?

Upgrade auto-gpt to 0.4.3 or later. Fixes are available for 2 affected products.

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.

CWE-117

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

35thpercentile

Low risk: more likely to be exploited than 35% of all known CVEs.

References

Patch2

Related Vulnerabilities

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

CVE	Severity	CVSS	EPSS	Exploited	Fix
CVE-2021-43410	Medium	5.3	2.4%	-	Fix
CVE-2022-32549	Medium	5.3	2.3%	-	-
CVE-2019-14864	Medium	6.5	1.9%	-	Fix
CVE-2021-42250	Medium	6.5	1.8%	-	Fix
CVE-2024-47083	High	7.5	1.6%	-	-
CVE-2020-25646	High	7.5	1.4%	-	-

Embed a live status badge for CVE-2023-37275

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 works Start 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.