CVE-2025-53944: AutoGPT Platform Exposes Graph Execution Results via Authorization Gap
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 getgraphexecutionresults endpoint has an authorization bypass vulnerability. While it correctly validates user access to the graphid, it fails to verify ownership of the graphexecid 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.
Affected Software
Remediation
Event History
Frequently Asked Questions
What is the severity of CVE-2025-53944?
CVE-2025-53944 is classified as a high severity vulnerability due to its potential for unauthorized access.
How do I fix CVE-2025-53944?
To mitigate CVE-2025-53944, upgrade AutoGPT to version 0.6.16 or later which addresses the authorization bypass.
What software is affected by CVE-2025-53944?
CVE-2025-53944 affects AutoGPT versions 0.6.15 and below.
What is the main issue with CVE-2025-53944?
The main issue with CVE-2025-53944 is an authorization bypass in the get_graph_execution_results endpoint.
Who is impacted by CVE-2025-53944?
Anyone using AutoGPT versions 0.6.15 or earlier may be impacted by CVE-2025-53944.