CVSS Score of 10 (low)


Published Jul 13, 2023
Updated: Jul 27, 2023
CWE ID 117


CVE-2023-37275 is a vulnerability that affects Auto-GPT, an experimental open-source application showcasing the capabilities of the GPT-4 language model. Before version 0.4.3, this vulnerability allowed malicious external resources, such as a website visited by Auto-GPT, to manipulate and print misleading messages to the console by utilizing JSON encoded ANSI escape sequences. These escape sequences were decoded and displayed as part of the model's "thinking process". The issue has been addressed and patched in release version 0.4.3, mitigating the potential danger it poses to organizations using Auto-GPT.

Leverage our Vulnerability Intelligence module to secure your systems now - get detailed insights on CVE-2024-37364. Book your demo today.


Explore Beyond the CVE Basics with Recorded Future's Vulnerability Intelligence

Note: This is just a basic overview providing quick insights into CVE-2023-37275 information. Gain full access to comprehensive CVE data, risk scores, prioritization, and mitigation data through Recorded Future's Vulnerability Intelligence:
  • Prioritize with Risk-Based Scoring
  • Explore the Extensive Vulnerability Database
  • Receive Early Alerts on Emerging CVEs
  • Focus on Critical Exploitable Vulnerabilities
  • Streamline Remediation with Integration Options