CVE Feed

    Dashboard / CVE / CVE-2023-37275

    CVE-2023-37275

    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:Jul 13, 2023
    Last Modified:Feb 24, 2026
    EPS:Jul 13, 2023
    EPSS Score:0.00064
    CVSS Score:3.1

    Affected Products

    Vendor
    Agpt
    Product
    Autogpt Classic

    Exploits

    No exploit reference

    Related CVEs

    CVE-2024-8156 (CVSS 9.8) — A command injection vulnerability exists in the workflow-checker.yml workflow of significant-gravitas/autogpt.…
    CVE-2024-6091 (CVSS 9.8) — A vulnerability in significant-gravitas/autogpt version 0.5.1 allows an attacker to bypass the shell commands …
    CVE-2024-1880 (CVSS 7.8) — An OS command injection vulnerability exists in the MacOS Text-To-Speech class MacOSTTS of the significant-gra…
    CVE-2024-1881 (CVSS 9.8) — AutoGPT, a component of significant-gravitas/autogpt, is vulnerable to an improper neutralization of special e…
    CVE-2024-1879 (CVSS 8.8) — A Cross-Site Request Forgery (CSRF) vulnerability in significant-gravitas/autogpt version v0.5.0 allows attack…
    CVE-2023-37274 (CVSS 7.5) — Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. W…
    CVE-2023-37273 (CVSS 8.1) — Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. R…

    Common Vulnerability Scoring System

    Attack Vector
    Network
    Adjacent
    Local
    Physical
    Privileges Required
    None
    Low
    High
    User Interaction
    None
    Required
    Scope
    Unchanged
    Changed
    Confidentiality
    None
    Low
    High
    Integrity
    None
    Low
    High
    Availability
    None
    Low
    High