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.
Contaban con certificados de procedencia válidos, y el malware se ejecutaba cuando se cargaban los módulos afectados, no en el momento de la instalación.
Leer artículo →Una solicitud de extracción maliciosa puede eludir las revisiones de código sin problemas. Días después, obliga a un asistente de IA a extraer secretamente info...
Leer artículo →Recientemente, ejecutivos de Microsoft publicaron una entrada oficial en su blog donde detallan una experiencia de búsqueda mejorada para los participantes del...
Leer artículo →