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.
Fortinet reveló una vulnerabilidad crítica de omisión de autenticación en la interfaz gráfica de usuario de FortiSandbox que podría permitir a atacantes remotos...
Leer artículo →Microsoft ha confirmado que los usuarios sin privilegios de administrador podrían no poder conectarse a dispositivos mediante Escritorio remoto tras instalar la...
Leer artículo →Microsoft ha corregido una vulnerabilidad de día cero en Windows Shell que se explotaba activamente y que permitía a los atacantes eludir las protecciones de la...
Leer artículo →