CVE-2025-53944 | AutoGPT Platform Exposes Graph Execution Results via Authorization Gap
Exp
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.
Conclusion & alert: CVE-2025-53944 is rated High Exploit Risk (69/100): CVSS High severity, with medium exploitation likelihood (EPSS 0.48%).Core evidence: 1 public exploit reference(s) are indexed (Exploit-DB).Mandatory action: Public exploits are available—assess exposure, apply mitigations, and prioritize patching.
Risk is dynamic; we continuously reassess and refresh what is shown on this page as upstream context changes.
Public exploit references (Exploit-DB) for CVE-2025-53944
Exploit prediction scoring system (EPSS) score for CVE-2025-53944
EPSS lead: Daily EPSS estimates relative likelihood of exploitation; percentile ranks this CVE among scored vulnerabilities (higher = more severe relative rank).