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