CVE-2025-53944 AutoGPT Platform Exposes Graph Execution Results via Authorization Gap

High 7.7 Published 30 Jul 2025 Updated 30 Jul 2025

Authenticated users can access arbitrary graph execution results by bypassing ownership checks on the external API endpoint.

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-2025-53944?

CVE-2025-53944 is a high-severity missing authorization vulnerability in Significant-Gravitas AutoGPT, published on 30 Jul 2025. 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. In v0.6.15 and below, the external API's get_graph_execution_results endpoint has an authorization bypass vulnerability. While it correctly validates user access to the graph_id, it fails to verify ownership of the graph_exec_id parameter, allowing authenticated users to access any execution results by providing arbitrary execution IDs. The internal API implements proper validation for both parameters. This is fixed in v0.6.16.

Weakness: CWE-639, CWE-285

Which versions are affected by CVE-2025-53944?

It affects 1 product.

Products include Agpt Autogpt Platform.

How do I fix CVE-2025-53944?

No fix has been published for CVE-2025-53944 yet. Limit exposure of the affected software until one is available.

Upgrade, and check permissions on every request on the server, not only in the interface. More about Missing authorization.

Is CVE-2025-53944 being exploited?

It is not confirmed as exploited in the wild, but public exploit code for CVE-2025-53944 exists.

Sources

Also known as GHSA-x77j-qg2x-fgg6.