CVE-2026-26020 AutoGPT Affected by Remote Code Execution via Dynamic Module Import in Block Loading (__import__)
Authenticated users can execute arbitrary code on the server by bypassing disabled block restrictions in graph configurations.
- Exploited in the wild
- Not known
- Login needed
- Any signed-in user
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2026-26020?
CVE-2026-26020 is a critical code injection vulnerability in Significant-Gravitas AutoGPT, published on 12 Feb 2026. Any signed-in user can exploit it over the network, with no action from the victim.
Official 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.
Weakness: CWE-285
Which versions are affected by CVE-2026-26020?
It affects 1 product.
Products include Agpt Autogpt Platform.
How do I fix CVE-2026-26020?
No fix has been published for CVE-2026-26020 yet. Limit exposure of the affected software until one is available.
Upgrade, and never evaluate templates, expressions or code built from user input. More about Code injection.
Is CVE-2026-26020 being exploited?
There is no known exploitation of CVE-2026-26020 in the wild and no public exploit code.
Other vulnerabilities in Significant-Gravitas AutoGPT
- CVE-2025-62615 AutoGPT has SSRF vulnerability in ReadRSSFeedBlock
- CVE-2025-62616 AutoGPT has SSRF vulnerability in SendDiscordFileBlock
- CVE-2025-1040 Server-Side Template Injection (SSTI) in significant-gravitas/autogpt
- CVE-2025-32393 AutoGPT has a DoS vulnerability in ReadRSSFeedBlock
- CVE-2026-24780 AutoGPT is Vulnerable to RCE via Disabled Block Execution
Sources
Also known as GHSA-4crw-9p35-9x54.