CVE-2024-1881 Improper Neutralization of Special Elements used in an OS Command in significant-gravitas/autogpt

High 8.8 Published 6 Jun 2024 Updated 1 Aug 2024

Attackers can execute arbitrary shell commands by bypassing command validation in AutoGPT, requiring an upgrade to secure the application.

Exploited in the wild: Not known
Login needed: Any signed-in user
Attackable: Over the internet
Victim action needed: Not needed
Fix: None listed

What is CVE-2024-1881?

CVE-2024-1881 is a high-severity command injection vulnerability in significant-gravitas/autogpt, published on 6 Jun 2024. Any signed-in user can exploit it over the network, with no action from the victim.

Official description

AutoGPT, a component of significant-gravitas/autogpt, is vulnerable to an improper neutralization of special elements used in an OS command ('OS Command Injection') due to a flaw in its shell command validation function. Specifically, the vulnerability exists in versions v0.5.0 up to but not including 5.1.0. The issue arises from the application's method of validating shell commands against an allowlist or denylist, where it only checks the first word of the command. This allows an attacker to bypass the intended restrictions by crafting commands that are executed despite not being on the allowlist or by including malicious commands not present in the denylist. Successful exploitation of this vulnerability could allow an attacker to execute arbitrary shell commands.

Weakness: CWE-78

Which versions are affected by CVE-2024-1881?

It affects 1 product.

Products include Agpt Autogpt Classic.

How do I fix CVE-2024-1881?

No fix has been published for CVE-2024-1881 yet. Limit exposure of the affected software until one is available.

Upgrade, and pass arguments to programs as a list instead of through a shell. More about Command injection.

Is CVE-2024-1881 being exploited?

It is not confirmed as exploited in the wild, but public exploit code for CVE-2024-1881 exists.

Sources

Also known as GHSA-rr88-j2r8-3xpc.