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.
Amazon Web Services (AWS) ha confirmado que parte de los datos de sus clientes alojados en centros de datos de Oriente Medio son irrecuperables de forma permane...
Leer artículo →Una vulnerabilidad crítica en los servidores de gestión de seguridad y de registro (log servers) de Check Point podría permitir a un atacante sin credenciales d...
Leer artículo →Una brecha de seguridad en Gyazo, el servicio de intercambio de imágenes de Helpfeel, expuso alrededor de 23,62 millones de registros de usuarios —incluyendo di...
Leer artículo →