CVE-2026-26020: AutoGPT Affected by Remote Code Execution via Dynamic Module Import in Block Loading (__import__)
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.
Affected Software
Remediation
Event History
Frequently Asked Questions
What is the severity of CVE-2026-26020?
CVE-2026-26020 is classified as a high severity vulnerability due to its potential for remote code execution.
How do I fix CVE-2026-26020?
To fix CVE-2026-26020, upgrade AutoGPT to version 0.6.48 or later.
Who is affected by CVE-2026-26020?
CVE-2026-26020 affects all users of AutoGPT versions prior to 0.6.48.
What type of vulnerability is CVE-2026-26020?
CVE-2026-26020 is a remote code execution vulnerability that arises from improper handling of dynamic module imports.
Can CVE-2026-26020 be exploited by unauthenticated users?
No, CVE-2026-26020 requires an authenticated user for exploitation.