CVE-2026-26020

Critical
|9.4
No Exploit

Plain English Summary

AI-powered analysis for quick understanding

This vulnerability allows an authenticated user to run malicious code on the backend server of the AutoGPT platform, potentially taking full control of the system. It occurs because the platform fails to properly enforce restrictions on a development tool, enabling users to bypass security measures by embedding it in their workflows.

Technical 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.

CVSS Vector Analysis

Attack VectorNetwork
Attack ComplexityLow
Privileges RequiredLow
User InteractionNone
Confidentiality ImpactHigh
Integrity ImpactHigh
Availability ImpactHigh
ScopeChanged

Vector String

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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

Exploit Resources

Search for proof-of-concept code and exploit modules

Official References

Est. Bounty
$9,000($5K-$15K)
Vendor Response
Grade APatched in 4 days

Quick Information

Published

Feb 12, 2026

8 days ago

Last Modified

Feb 17, 2026

3 days ago

Vendor

agpt

Product

autogpt platform