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.
Una nueva investigación revela que el contenido de un correo electrónico puede traspasar los límites del mensaje e interferir con la interfaz de correo web. Med...
Leer artículo →Investigadores de 1Password descubrieron que los modelos de IA solo solucionan vulnerabilidades de seguridad correctamente en un 26% de los casos, a menudo intr...
Leer artículo →Se están utilizando ataques tipo ClickFix para distribuir un malware basado en Go capaz de robar criptomonedas, contraseñas almacenadas en el navegador, datos d...
Leer artículo →