CVE-2023-37275
Agpt Autogpt Classic ≤ 0.4.3
Raw vector
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:N/I:L/A:NSummary
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
- 🇪🇺 ENISA EUVD: EUVD-2023-41186
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
CVEs Like This One
Affected Assets
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.
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.
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.
Security testing can detect log injection flaws but does not prevent them at the source.
Logging control directly requires proper log generation and handling, which mitigates improper output neutralization.
Monitoring activities rely on trustworthy logs but do not ensure log message integrity.
Secure SDLC includes coding standards that reduce log-related weaknesses but does not specifically address logging.
Secure coding practices mandate input validation and output encoding, directly preventing log injection.