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.
Meta anunció el martes una serie de funciones de seguridad para las cuentas de WhatsApp, incluyendo la compatibilidad con múltiples contraseñas para una misma c...
Leer artículo →Los ciberdelincuentes ya han comprometido más de 270 instancias de Zimbra mediante ataques de ejecución remota de código que explotan una vulnerabilidad de alta...
Leer artículo →Un ingenioso investigador logró que la función Buscar mi iPhone de Apple funcionara en un entorno totalmente ajeno a la red de Apple. Un especialista en segurid...
Leer artículo →