vulntracker.iovulntracker.io
© 2026 vulntracker.io

CVE-2023-37275

System logs spoofable in Auto-GPT via ANSI control sequences

MEDIUM
4.3
CVSS Score
Published: July 13, 2023 at 10:34 PM UTC
Updated: June 17, 2026 at 06:07 AM UTC
2 products affected across 2 vendorsAutogpt ClassicAutoGPT

Using Auto-GPT by Significant-Gravitas?

Get instant alerts when new vulnerabilities affect Auto-GPT - before attackers find them.

Real-time alertsTrack your software stackFree plan available
Start FreeSign In
Severity
MEDIUM4.3
Exploit prediction
EPSS 0.4%
SSVC
No known exploit

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.

Affected

Our own answer: ranges merged, affected separated from platform-only, with confidence and review flags.

Autogpt Classic· Agpt
95%
v < 0.4.3
AutoGPT· Significant Gravitas
60%
v < 0.4.3
Affected range stops below 0.4.3, so it looks safe — our inference, not a vendor statement

Remediation

No guide yet

No remediation guidance has been written for this CVE yet. What the record does show:

Patch and advisory references

References (2)

x_refsource_MISCPatchThird Party Advisory
Source: [email protected]
https://github.com/Significant-Gravitas/Auto-GPT/pull/4810
x_refsource_CONFIRMPatchThird Party Advisory
Source: [email protected]
https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-r7f7-qrrv-3fjh

SSVC — Action Prioritization

SSVCNo known exploitNot automatablePartial impact

SSVC signals action urgency (what to patch first), separate from CVSS which measures severity.

CVSS

4.3MEDIUM[email protected]
Attack Vector
NETWORK
Complexity
LOW
Privileges
NONE
User Interaction
REQUIRED
Scope
UNCHANGED
Confidentiality
NONE
Integrity
LOW
Availability
NONE
Vector?

Quick Info

StatusANALYZED
CWE
CWE-117

Get alerted

Stop reading CVE feeds looking for your own stack

Track the products you run and VulnTracker tells you when a new CVE affects them — with what is known about fixing it, and nothing about the rest.

Create accountSign in
Free plan, no card