Security Resilience

CVE-2023-37275

Agpt Autogpt Classic ≤ 0.4.3

Published
13 July 2023
Modified
24 February 2026
Patch / advisory
View advisory
CVSS Score v3.1 3.1
Click a component to see what it means
Raw vectorCVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:N/I:L/A:N
EPSS Score 0.0044 36th percentile
Risk Priority 29 floored blend · peak EPSS

CVSS and EPSS are reproduced from their sources (NVD, FIRST EPSS). Risk Priority is our own derived reading, not an NVD score.

Summary

CVE-2023-37275 is a low-severity Improper Output Neutralization for Logs (CWE-117) vulnerability in Agpt Autogpt Classic. Its CVSS base score is 3.1 (Low).

Operationally, exploitation aligns with the MITRE ATT&CK technique Data Obfuscation (T1001); ranked at the 36th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.

This vulnerability is AI-related — categorised as LLM Application Platforms.

OWASP Top 10 for Web (2025)

A09:2025 Security Logging and Alerting Failures

EU & UK References

Vulnerability Data

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…

more

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(s)
CWE-117

AI Security AnalysisAI

AI Category
LLM Application Platforms
Risk Domain
N/A
OWASP Top 10 for LLMs 2025
None mapped
AI-specific weaknesses CR
CWE-1426
  • CWE-1426 — LLM output with ANSI escapes reaches console sink without sanitization.
Mapped by Security Resilience · not in NVD. Poisoning and extraction cases are routed to MITRE ATLAS instead of a synthetic CWE.
Classification Reason
Matched keywords: gpt, gpt, gpt, gpt, llm

Related Threats

MITRE ATT&CK Enterprise Techniques

T1001 Data Obfuscation Command And Control
Adversaries may obfuscate command and control traffic to make it more difficult to detect.
attack.mitre.org →
T1001.002 Steganography Command And Control
Adversaries may use steganographic techniques to hide command and control traffic to make detection efforts more difficult.
attack.mitre.org →
T1003.001 LSASS Memory Credential Access
Adversaries may attempt to access credential material stored in the process memory of the Local Security Authority Subsystem Service (LSASS).
attack.mitre.org →
T1003.003 NTDS Credential Access
Adversaries may attempt to access or create a copy of the Active Directory domain database in order to steal credential information, as well as obtain other information about domain members such as devices, users, and access rights.
attack.mitre.org →
T1003.005 Cached Domain Credentials Credential Access
Adversaries may attempt to access cached domain credentials used to allow authentication to occur in the event a domain controller is unavailable.
attack.mitre.org →
T1003.008 /etc/passwd and /etc/shadow Credential Access
Adversaries may attempt to dump the contents of <code>/etc/passwd</code> and <code>/etc/shadow</code> to enable offline password cracking.
attack.mitre.org →
Derived from this CVE’s CWE(s) via the direct CWE→ATT&CK cross-walk.

CVEs Like This One

CVE-2023-37274Same product: Agpt Autogpt Classic
CVE-2023-37273Same product: Agpt Autogpt Classic
CVE-2024-6091Same product: Agpt Autogpt Classic
CVE-2024-8156Same product: Agpt Autogpt Classic
CVE-2024-1881Same product: Agpt Autogpt Classic
CVE-2024-1880Same product: Agpt Autogpt Classic
CVE-2024-1879Same product: Agpt Autogpt Classic
CVE-2024-12580Shared CWE-117
CVE-2025-11627Shared CWE-117
CVE-2026-9016Shared CWE-117

Affected Assets

agpt
autogpt classic
≤ 0.4.3

Mitigating Controls

Likely Mitigating Controls AI

Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.

AU-1 Policy and Procedures
addresses: CWE-117

Policy and procedures require sanitization and neutralization when generating audit logs to avoid injection issues.

SI-15 Information Output Filtering
addresses: CWE-117

Requiring output to conform to expected content prevents unneutralized data from reaching logs.

Mitigating Controls (NIST CSF 2.0) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.

PR.PS-06 partial match
blocks

Secure SDLC practices and coding standards directly require output sanitization for logs.

Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.

A.8.15 Logging partial match
removes

A.8.15 records, protects, and analyzes logs but never mandates or performs output neutralization/escaping of external data written into log messages, so the first-party code defect named by CWE-117 remains present after the control is implemented

A.8.16 Monitoring activities partial match
finds

Monitoring activities rely on trustworthy logs but do not ensure log message integrity.

A.8.19 Installation of software on operational systems partial match
removes
A.8.25 Secure development life cycle partial match
blocks

Secure SDLC includes coding standards that reduce log-related weaknesses but does not specifically address logging.

A.8.26 Application security requirements partial match
removes
A.8.27 Secure system architecture and engineering principles partial match
removes

References