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.
Check Point ha advertido que atacantes están explotando activamente dos vulnerabilidades críticas en sus productos de VPN y gestión, lo que permite el acceso re...
Leer artículo →Cisco Talos ha lanzado CAIRN, un kit de herramientas de código abierto diseñado para rastrear, clasificar y detectar malware integrado con IA. Esta red de inves...
Leer artículo →La dirección de correo electrónico privada que GitLab te proporciona para reportar incidencias por correo electrónico es una credencial. Cualquiera que la obten...
Leer artículo →