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.
Los hackers están explotando activamente una vulnerabilidad en la biblioteca Java de código abierto FastJson, que permite la ejecución remota de código sin inte...
Leer artículo →El proyecto Apache Fory reveló cuatro vulnerabilidades el 21 de julio de 2026. Tres de ellas son de gravedad importante y una de gravedad moderada. La versión 1...
Leer artículo →n8n ha corregido una vulnerabilidad de alta gravedad que permitía a un editor de flujos de trabajo autenticado ejecutar comandos del sistema operativo en el ser...
Leer artículo →