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.
¿Qué grabaste por última vez en tu iPhone? Quizás una conferencia, una llamada con tu casero o las notas de una cita médica que querías recordar. Tanto si usast...
Leer artículo →Guardz, la plataforma de seguridad para espacios de trabajo con agentes diseñada para proveedores de servicios gestionados (MSP), anunció hoy la integración de...
Leer artículo →Cogent Security, una empresa de ciberseguridad basada en IA aplicada, informó que la vulnerabilidad PHP2Shell expuso importantes deficiencias en la respuesta em...
Leer artículo →