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 servicio japonés de coches compartidos Times Car ha confirmado que aproximadamente 6,6 millones de cuentas de usuario se vieron comprometidas en un ciberataq...
Leer artículo →NVIDIA ha lanzado la Plataforma Abierta de Seguridad para Agentes (Open Agent Safety Platform), un marco abierto diseñado para proteger a los agentes de IA autó...
Leer artículo →La empresa tecnológica estadounidense Kiteworks ha levantado la advertencia preventiva que solicitaba a sus clientes que apagaran sus sistemas tras corregir una...
Leer artículo →