CVE-2023-37273
Agpt Autogpt Classic ≤ 0.4.3
Raw vector
CVSS:3.1/AV:L/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:LSummary
CVE-2023-37273 is a high-severity Code Injection (CWE-94) vulnerability in Agpt Autogpt Classic. Its CVSS base score is 8.1 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Command and Scripting Interpreter (T1059); ranked at the 29th 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-2023-41184
Vulnerability Data
Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. Running Auto-GPT version prior to 0.4.3 by cloning the git repo and executing `docker compose run auto-gpt` in the repo root uses a different docker-compose.yml file…
more
from the one suggested in the official docker set up instructions. The docker-compose.yml file located in the repo root mounts itself into the docker container without write protection. This means that if malicious custom python code is executed via the `execute_python_file` and `execute_python_code` commands, it can overwrite the docker-compose.yml file and abuse it to gain control of the host system the next time Auto-GPT is started. The issue has been patched in 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
- Classification Reason
- Matched keywords: gpt, gpt, gpt, gpt, gpt
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
—
—
—
V1.3.1
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.
Makes persistent code injection into loaded programs impossible when the executable image itself resides on hardware-protected read-only media.
Dynamically generated code can be produced and executed inside the isolated chamber, preventing host compromise from code-injection payloads.
Validates inputs used in dynamic code generation to block injected directives.
Directly prevents execution of attacker-supplied code written into data memory regions.
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's SDLC practices directly target injection flaws via secure coding and testing (mostly), yet as a single broad outcome it leaves many code-generation specifics unaddressed (partial).
PR.DS-10 protects runtime data confidentiality/integrity but has no bearing on neutralizing externally influenced input during code generation, so neither direction shows any preventive effect.
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.
Banning unapproved code samples and unauthenticated web services, combined with secure-coding standards and SAST, prevents the dynamic generation or inclusion of attacker-supplied code.
Controls that restrict unauthorized or malicious code from being introduced via external networks or removable media limit opportunities for an attacker to inject and execute arbitrary code.