CVE-2026-72922: Improper Authentication

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.70, AutoGPT's autogptplatform/backend/backend/api/features/integrations/router.py webhookingressgeneric route selected getwebhookmanagerprovider from the untrust...

Security Bulletin: Parameter Injection Vulnerability in API Graph Execution Engine

Summary A parameter injection vulnerability existed in the API Graph Execution Engine's tweaks processing mechanism. The vulnerability allowed authenticated attackers to bypass security controls and inject malicious parameters into flow components at runtime. An attacker with valid API credential...

PT-2026-44553

Name of the Vulnerable Software and Affected Versions AutoGPT versions prior to 0.6.59 Description AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. The 'POST /api/blocks/block id/execute' endpoint allows the execution of...

Aegra 授权问题漏洞

Aegra is a large-scale model application platform developed by Aegra Corporation, designed for building and orchestrating multi-step intelligent agent processes. Versions of Aegra prior to 0.9.7 contained an authorization vulnerability. This vulnerability stemmed from multiple authenticated users...

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 ...

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 ...

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 ...