HighVulnerabilityLLM-specific

CVE-2023-37273: Auto-GPT docker-compose.yml overwrite through Python code execution

Source: NVD(opens in a new tab)
Identifier: CVE-2023-37273
Published: July 13, 2023
Record updated: October 9, 2026

Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.4%

Summary

Auto-GPT versions prior to 0.4.3, when started from the cloned repo with `docker compose run auto-gpt`, use a docker-compose.yml that mounts itself into the container without write protection. Malicious Python code run through `execute_python_file` or `execute_python_code` can overwrite that file and use it to take control of the host system on the next start.

Mitigation

Fixed in 0.4.3.

Details

Scores and exploitation

CVSS score: 8.1(high)
EPSS: 0.4%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 4, 2026.

Weaknesses and techniques

Weakness (CWE): CWE-94
Attack pattern (CAPEC): CAPEC-242

Affected

Vendors: OpenAI

Classification

Attack type: Other
Attack sophistication: Moderate
AI component targeted: Agent
Impact: Integrity,
Confidentiality,
Availability
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2023-37273

First tracked: February 15, 2026 at 08:53 PM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 95% (self-assessed)

Summary

Mitigation

Related items