CVE-2023-37275

    Dashboard / Vulnerabilities / CVE-2023-37275

    CVE-2023-37275

    Published: 13 Jul 2023Last Modified: 12 Aug 2026

    Summary: System logs spoofable in Auto-GPT via ANSI control sequences

    Details: 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.

    References: https://github.com/CVEProject/cvelistV5/tree/main/cves/2023/37xxx/CVE-2023-37275.json, https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-r7f7-qrrv-3fjh, https://nvd.nist.gov/vuln/detail/CVE-2023-37275, https://github.com/Significant-Gravitas/Auto-GPT/pull/4810

    Affected packages

    Package

    Name:

    Purl:

    Affected ranges

    Type: GIT

    Events:

    Introduced- 0
    Fixed -80151dd6b2870dc6f91aafadb3a451f2e440a3ba

    Affected versions

    v0.4.1
    v0.4.0

    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
    CVE-2023-37275 | CVE-DB