CVE-2026-26020 AutoGPT Affected by Remote Code Execution via Dynamic Module Import in Block Loading (__import__)
- Published
- Updated
- Exploit status
- No public exploit known
- CISA SSVC
- No known exploitation · automatable: no · technical impact: total
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.
Upgrade path
2 packages: 1 fixed.
| Package | Affected | Fixed in | Status |
|---|---|---|---|
| agpt autogpt platform | < 0.6.48 | 0.6.48 | Fixed |
| Significant-Gravitas AutoGPT | = < 0.6.48 | No fix listed | Versions listed |
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| Significant-Gravitas AutoGPT | = < 0.6.48 | No fix listed |
| agpt autogpt platform | < 0.6.48 | 0.6.48 |
References
- https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-4crw-9p35-9x54 mitigation vendor-advisory
- https://github.com/Significant-Gravitas/AutoGPT/commit/062fe1aa709217136b896c8b950e0f04435afb32 patch
- https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.6.48 release-notes