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.
Cerca de 22.000 servidores Microsoft Exchange expuestos en línea permanecen sin parchear ante una vulnerabilidad de omisión de autenticación de alta gravedad qu...
Leer artículo →Socket descubrió 19 extensiones de navegador maliciosas que roban criptomonedas. Las extensiones se lanzan inicialmente sin malware y, una vez que ganan confian...
Leer artículo →Microsoft está investigando un problema que provoca que el software de seguridad Defender para Office 365 marque erróneamente enlaces legítimos de búsqueda de G...
Leer artículo →