Cyber Resilience

CVE-2023-37275

Agpt Autogpt Classic ≤ 0.4.3

Published
13 July 2023
Modified
24 February 2026
Patch / 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

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 Indicator Removal (T1070); 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)

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)

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 — LLM output with ANSI escapes reaches console sink without sanitization.
Mapped by Cyber 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

T1070 Indicator Removal Stealth
Adversaries may selectively delete or modify artifacts generated to reduce indications of their presence and blend in with legitimate activity.
Derived from this CVE’s CWE(s) via the direct CWE→ATT&CK cross-walk.

CVEs Like This One

CVE-2023-37273Same product: Agpt Autogpt Classic
CVE-2023-37274Same product: Agpt Autogpt Classic
CVE-2024-6091Same product: Agpt Autogpt Classic
CVE-2024-1879Same product: Agpt Autogpt Classic
CVE-2024-1881Same product: Agpt Autogpt Classic
CVE-2024-8156Same product: Agpt Autogpt Classic
CVE-2024-1880Same product: Agpt Autogpt Classic
CVE-2024-12580Shared CWE-117
CVE-2024-52962Shared CWE-117
CVE-2024-7696Shared 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.

addresses: CWE-117

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

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 mostly match
prevents

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.

finds

Security testing can detect log injection flaws but does not prevent them at the source.

A.8.15 Logging partial match
degrades

Logging control directly requires proper log generation and handling, which mitigates improper output neutralization.

finds

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

prevents

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

prevents

Secure coding practices mandate input validation and output encoding, directly preventing log injection.

References