CVE-2026-26020: critical vulnerability in Significant-Gravitas AutoGPT
AutoGPT Affected by Remote Code Execution via Dynamic Module Import in Block Loading (__import__)
Published
E-mail alert when it lands in KEV, gets a public PoC or its score goes up.
28Vexday Risk Score
No sign of exploitation. No public exploitation artifact known so far.
ssvc Trackcvss 9.4epss 0.6%
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:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H
Affected products
Significant-Gravitas · AutoGPTRelated CVEs — Significant-Gravitas AutoGPT
In the same product, most dangerous first.
CVE-2026-24780HIGHAutoGPT is Vulnerable to RCE via Disabled Block ExecutionEPSS 1.3%CVE-2025-22603HIGHAutoGPT SSRF vulnerabilityEPSS 0.6%CVE-2025-53944HIGHAutoGPT Platform Exposes Graph Execution Results via Authorization GapEPSS 0.5%CVE-2026-26006MEDIUMRedos (Regular Expression Denial of Service) at Code Extraction Block in significant-gravitas/autogptEPSS 0.5%CVE-2025-31490HIGHAutoGPT allows SSRF due to DNS Rebinding in requests wrapperEPSS 0.5%CVE-2025-31491HIGHAutoGPT allows leakage of cross-domain cookies and protected headers in requests redirectEPSS 0.5%