Home

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.

PUBLISHED Reserved 2026-02-09 | Published 2026-02-12 | Updated 2026-02-12 | Assigner GitHub_M




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

Problem types

CWE-285: Improper Authorization

Product status

< 0.6.48
affected

References

github.com/...utoGPT/security/advisories/GHSA-4crw-9p35-9x54

github.com/...ommit/062fe1aa709217136b896c8b950e0f04435afb32

github.com/...GPT/releases/tag/autogpt-platform-beta-v0.6.48

cve.org (CVE-2026-26020)

nvd.nist.gov (CVE-2026-26020)

Download JSON