CVE-2025-53944

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.

CVSS v3 7.7 HIGH

7.7^/10

CVSS v3 : HIGH

Vector :

Exploitability : 3.1 / Impact : 4.0

Attack Vector NETWORK

Attack Complexity LOW

Privileges Required LOW

User Interaction NONE

Confidentiality Impact HIGH

Integrity Impact NONE

Availability Impact NONE

Scope CHANGED

References

Link	Resource
https://github.com/Significant-Gravitas/AutoGPT/commit/309114a727baa2063357810d444e9a119f8dd7f6	Patch
https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.6.16	Release Notes
https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-x77j-qg2x-fgg6	Exploit Vendor Advisory
https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-x77j-qg2x-fgg6	Exploit Vendor Advisory

Configurations

Configuration 1 (hide)

cpe:2.3:a:agpt:autogpt_platform:0.6.13:beta:*:*:*:*:*:*

History

No history.

Information

Published : 2025-07-30 15:15

Updated : 2025-08-05 14:40

NVD link : CVE-2025-53944

Mitre link : CVE-2025-53944

CVE.ORG link : CVE-2025-53944

JSON object : View

Products Affected

agpt

autogpt_platform

CWE

CWE-285

Improper Authorization

CWE-639

Authorization Bypass Through User-Controlled Key

{"id": "CVE-2025-53944", "cveTags": [], "metrics": {"cvssMetricV31": [{"type": "Secondary", "source": "[email protected]", "cvssData": {"scope": "CHANGED", "version": "3.1", "baseScore": 7.7, "attackVector": "NETWORK", "baseSeverity": "HIGH", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N", "integrityImpact": "NONE", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "NONE", "privilegesRequired": "LOW", "confidentialityImpact": "HIGH"}, "impactScore": 4.0, "exploitabilityScore": 3.1}, {"type": "Primary", "source": "[email protected]", "cvssData": {"scope": "CHANGED", "version": "3.1", "baseScore": 7.7, "attackVector": "NETWORK", "baseSeverity": "HIGH", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N", "integrityImpact": "NONE", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "NONE", "privilegesRequired": "LOW", "confidentialityImpact": "HIGH"}, "impactScore": 4.0, "exploitabilityScore": 3.1}]}, "published": "2025-07-30T15:15:35.210", "references": [{"url": "https://github.com/Significant-Gravitas/AutoGPT/commit/309114a727baa2063357810d444e9a119f8dd7f6", "tags": ["Patch"], "source": "[email protected]"}, {"url": "https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.6.16", "tags": ["Release Notes"], "source": "[email protected]"}, {"url": "https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-x77j-qg2x-fgg6", "tags": ["Exploit", "Vendor Advisory"], "source": "[email protected]"}, {"url": "https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-x77j-qg2x-fgg6", "tags": ["Exploit", "Vendor Advisory"], "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0"}], "vulnStatus": "Analyzed", "weaknesses": [{"type": "Primary", "source": "[email protected]", "description": [{"lang": "en", "value": "CWE-285"}]}, {"type": "Primary", "source": "[email protected]", "description": [{"lang": "en", "value": "CWE-639"}]}], "descriptions": [{"lang": "en", "value": "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."}, {"lang": "es", "value": "AutoGPT es una plataforma que permite a los usuarios crear, implementar y gestionar agentes de inteligencia artificial continua. En la versi\u00f3n v0.6.15 y anteriores, el endpoint get_graph_execution_results de la API externa presenta una vulnerabilidad de omisi\u00f3n de autorizaci\u00f3n. Si bien valida correctamente el acceso del usuario a graph_id, no verifica la propiedad del par\u00e1metro graph_exec_id, lo que permite a los usuarios autenticados acceder a cualquier resultado de ejecuci\u00f3n proporcionando IDs de ejecuci\u00f3n arbitrarios. La API interna implementa la validaci\u00f3n adecuada para ambos par\u00e1metros. Esto se solucion\u00f3 en la versi\u00f3n v0.6.16."}], "lastModified": "2025-08-05T14:40:34.370", "configurations": [{"nodes": [{"negate": false, "cpeMatch": [{"criteria": "cpe:2.3:a:agpt:autogpt_platform:0.6.13:beta:*:*:*:*:*:*", "vulnerable": true, "matchCriteriaId": "2ECBE188-9A84-43D7-B7C7-6788F08F576C"}], "operator": "OR"}]}], "sourceIdentifier": "[email protected]"}