CVE-2026-5971

A flaw has been found in FoundationAgents MetaGPT up to 0.8.1. This vulnerability affects the function ActionNode.xml_fill of the file metagpt/actions/action_node.py of the component XML Handler. Executing a manipulation can lead to improper neutralization of directives in dynamically evaluated code. The attack may be launched remotely. The exploit has been published and may be used. The project was informed of the problem early through a pull request but has not reacted yet.
References
Link Resource
https://github.com/FoundationAgents/MetaGPT/ Product
https://github.com/FoundationAgents/MetaGPT/issues/1928 Exploit Issue Tracking
https://github.com/FoundationAgents/MetaGPT/issues/1956 Issue Tracking
https://vuldb.com/submit/791734 Exploit Third Party Advisory VDB Entry
https://vuldb.com/vuln/356525 Third Party Advisory VDB Entry
https://vuldb.com/vuln/356525/cti Permissions Required VDB Entry
Configurations

Configuration 1 (hide)

cpe:2.3:a:deepwisdom:metagpt:*:*:*:*:*:*:*:*

History

26 Oct 2026, 21:10

Type Values Removed Values Added
Summary
  • (es) Se ha encontrado una falla en FoundationAgents MetaGPT hasta la versión 0.8.1. Esta vulnerabilidad afecta a la función ActionNode.xml_fill del archivo metagpt/actions/action_node.py del componente Gestor XML. La ejecución de una manipulación puede llevar a una neutralización inadecuada de directivas en código evaluado dinámicamente. El ataque puede lanzarse de forma remota. El exploit ha sido publicado y puede ser utilizado. Se informó al proyecto del problema con antelación a través de una solicitud de extracción, pero aún no ha reaccionado.

Information

Published : 2026-04-09 18:17

Updated : 2026-10-26 21:10


NVD link : CVE-2026-5971

Mitre link : CVE-2026-5971

CVE.ORG link : CVE-2026-5971


JSON object : View

Products Affected

deepwisdom

  • metagpt
CWE
CWE-94

Improper Control of Generation of Code ('Code Injection')

CWE-95

Improper Neutralization of Directives in Dynamically Evaluated Code ('Eval Injection')