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 Proyecto Rust ha eliminado versiones maliciosas de tres crates de Rust ampliamente utilizados de crates.io después de que una cuenta de mantenedor comprometi...
Leer artículo →OpenAI ha anunciado la política de Cero Retención de Datos para los clientes elegibles de su API que utilizan sus modelos de IA de vanguardia, junto con un nuev...
Leer artículo →Citrix ha advertido a sus clientes que protejan inmediatamente sus sistemas contra dos vulnerabilidades que afectan a las soluciones de acceso remoto seguro Net...
Leer artículo →