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.
El equipo de seguridad NebuSec publicó detalles técnicos y código de explotación funcional para una vulnerabilidad crítica de Linux. Esta vulnerabilidad, identi...
Leer artículo →OpenAI ha presentado GPT-6 Astra, un modelo de IA de vanguardia que, según la compañía, puede identificar vulnerabilidades de día cero y crear exploits funciona...
Leer artículo →Investigadores de seguridad descubrieron una campaña activa de ataque de fuerza bruta contra contraseñas en AWS dirigida a cuentas en la nube con altos privileg...
Leer artículo →