Skip to main content

Autogpt Classic CVE-2023-37275

MEDIUM
Improper Output Neutralization for Logs (CWE-117)
2023-07-13 security-advisories@github.com
4.3
CVSS 3.1 · NVD
Share

Severity by source

NVD PRIMARY
4.3 MEDIUM
AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:L/A:N

Primary rating from NVD · only source for this CVE.

CVSS VectorNVD

CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:L/A:N
Attack Vector
Network
Attack Complexity
Low
Privileges Required
None
User Interaction
Required
Scope
Unchanged
Confidentiality
None
Integrity
Low
Availability
None

Lifecycle Timeline

1
CVE Published
Jul 13, 2023 - 23:15 nvd
MEDIUM 4.3

DescriptionNVD

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.

AnalysisAI

Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. Rated medium severity (CVSS 4.3), this vulnerability is remotely exploitable, no authentication required, low attack complexity.

Technical ContextAI

This vulnerability is classified under CWE-117. 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. Affected products include: Agpt Autogpt Classic. Version information: version 0.4.3..

RemediationAI

A vendor patch is available. Apply the latest security update as soon as possible. Apply vendor patches when available. Implement network segmentation and monitoring as interim mitigations.

Share

CVE-2023-37275 vulnerability details – vuln.today

This site uses cookies essential for authentication and security. No tracking or analytics cookies are used. Privacy Policy