Skip to content

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

CriticalCVSS 9.8 EPSS 1.4%
Published
Updated
Exploit status
No public exploit known
CISA SSVC
Proof of concept public · automatable: no · technical impact: total

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.

Upgrade path

3 packages: 3 fixed.

PackageAffectedFixed inStatus
agpt autogpt classic >= 0.5.0, < 0.5.1 0.5.1 Fixed
Significant-Gravitas AutoGPT >= 0.5.0, < 5.1.0 5.1.0 Fixed
significant-gravitas/autogpt < 5.1.0 5.1.0 Fixed

Affected products

ProductAffected versionsFixed in
significant-gravitas/autogpt < 5.1.0 5.1.0
Significant-Gravitas AutoGPT >= 0.5.0, < 5.1.0 5.1.0
agpt autogpt classic >= 0.5.0, < 0.5.1 0.5.1

References