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.
Una nueva vulnerabilidad en Microsoft Copilot para Word revela cómo las indicaciones ocultas dentro de los documentos pueden transformar la edición rutinaria en...
Leer artículo →Ruby on Rails ha publicado correcciones para una vulnerabilidad crítica de Active Storage que podría permitir a atacantes no autenticados leer archivos arbitrar...
Leer artículo →OpenAI ha liberado el código fuente de Codex Security, una herramienta de línea de comandos y un SDK de TypeScript diseñados para ayudar a los desarrolladores a...
Leer artículo →