CVE-2023-37275 System logs spoofable in Auto-GPT via ANSI control sequences

Low 3.1 Published 13 Jul 2023 Updated 22 Oct 2024

Attackers can spoof system logs in Auto-GPT using ANSI escape sequences, potentially misleading users into executing malicious commands.

Exploited in the wild: Not known
Login needed: Not needed
Attackable: Over the internet
Victim action needed: A user has to click or open something
Fix: None listed

What is CVE-2023-37275?

CVE-2023-37275 is a low-severity vulnerability in Significant-Gravitas Auto-GPT, published on 13 Jul 2023. An attacker can exploit it over the internet without logging in, and only if a user opens a file or follows a link.

Official description

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.

Weakness: CWE-117

Which versions are affected by CVE-2023-37275?

It affects 1 product.

Products include Agpt Autogpt Classic.

How do I fix CVE-2023-37275?

No fix has been published for CVE-2023-37275 yet. Limit exposure of the affected software until one is available.

Is CVE-2023-37275 being exploited?

There is no known exploitation of CVE-2023-37275 in the wild and no public exploit code.

Sources

Also known as GHSA-r7f7-qrrv-3fjh.