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.
Seguramente lo has experimentado: ese momento de frustración cuando has desarrollado una sólida función de IA basada en un proveedor de modelos, y de repente ap...
Leer artículo →El Equipo de Respuesta a Emergencias Informáticas de Ucrania (CERT-UA) ha revelado detalles de una nueva campaña de ingeniería social orquestada por ciberdelinc...
Leer artículo →Google lanzó una nueva actualización de seguridad para Chrome en el canal estable. Esta corrige cinco vulnerabilidades graves de uso de memoria liberada que afe...
Leer artículo →