fuente: https://cybersecuritynews.com/plugin4shell-zero-click-rce/
Plugin4Shell is a high-severity, zero-click remote code execution vulnerability affecting major AI coding agents, including Anthropic Claude Code, OpenAI Codex, GitHub Copilot, and Google Gemini CLI.
The flaw allows a malicious plugin update to execute attacker-controlled code without requiring a user to click, approve, or reinstall anything.
Plugin4Shell targets the software supply chain behind AI agents rather than the AI models themselves. Modern coding agents can install plugins, skills, and extensions from community marketplaces.
These add-ons often inherit the same permissions as the developer running the agent, including access to local source code, cloud credentials, SSH keys, internal repositories, production systems, and secrets.
The issue lies in the way affected agents handle SHA-pinned plugin versions. Marketplace systems commonly pin a plugin to a specific Git commit hash after it has been reviewed. This is intended to ensure the agent installs the exact approved code rather than a newer or modified version.
GitHub ha anunciado que está introduciendo un nuevo firewall de paquetes como una vista previa para bloquear la instalación de paquetes npm sospechosos durante...
Leer artículo →Cisco ha lanzado parches para abordar un fallo de seguridad de severidad alta en el Software de Firewall Adaptivo ASA y el Software de Defensa contra Amenazas F...
Leer artículo →Por Farukh Rakhimov, Director de Cumplimiento, Protección de Datos e Información Segura en AdTech Holding. En marzo de 2026, el Grupo de Inteligencia de Amenaza...
Leer artículo →