CVE 9.4 CRITICAL

AutoGPT Affected by Remote Code Execution via Dynamic Module Import in Block Loading (__import__)_CVE-2026-26020

9.4 / 10
CRITICAL
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H

Description

AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. Prior to 0.6.48, an authenticated user could achieve Remote Code Execution (RCE) on the backend server by embedding a disabled block inside a graph. The BlockInstallationBlock — a development tool capable of writing and importing arbitrary Python code — was marked disabled=True, but graph validation did not enforce this flag. This allowed any authenticated user to bypass the restriction by including the block as a node in a graph, rather than calling the block's execution endpoint directly (which did enforce the flag). This vulnerability is fixed in 0.6.48.

AI Analysis

Remote Code Execution (RCE) vulnerability in AutoGPT via dynamic module import in block loading

Basic Information

ID CVE-2026-26020
Source GitHub_M
Published Feb 12, 2026 at 20:52
Modified Feb 12, 2026 at 21:04

Affected Product

Vendor Significant-Gravitas
Product AutoGPT
Version < 0.6.48
Affected Versions Significant-Gravitas AutoGPT < 0.6.48

CWE Classification

AI Assessment

AI Score 9.4 / 10
AI Severity Critical
Vendor Significant-Gravitas
Product AutoGPT
Version < 0.6.48

References

💭 Join the Security Discussion

🔒 Your email address will not be published. Required fields are marked *

⚠️ Please be respectful and constructive in your comments. Security discussions should remain professional.