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 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.
Published 2023-07-13 23:15:11
Updated 2023-07-27 14:55:32
Source GitHub, Inc.
View at NVD,   CVE.org

Exploit prediction scoring system (EPSS) score for CVE-2023-37275

0.05%
Probability of exploitation activity in the next 30 days EPSS Score History
~ 14 %
Percentile, the proportion of vulnerabilities that are scored at or less

CVSS scores for CVE-2023-37275

Base Score Base Severity CVSS Vector Exploitability Score Impact Score Score Source First Seen
4.3
MEDIUM CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:L/A:N
2.8
1.4
NIST
3.1
LOW CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:N/I:L/A:N
1.6
1.4
GitHub, Inc.

CWE ids for CVE-2023-37275

References for CVE-2023-37275

Products affected by CVE-2023-37275

This web site uses cookies for managing your session, storing preferences, website analytics and additional purposes described in our privacy policy.
By using this web site you are agreeing to CVEdetails.com terms of use!