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.
Las brechas de seguridad no siempre comienzan con una vulnerabilidad de día cero. Un panel de administración expuesto puede ser atacado mediante fuerza bruta, o...
Leer artículo →Para los equipos de seguridad, los hallazgos son constantes, pero mantener la confianza en saber cuáles son relevantes se está volviendo más difícil. El problem...
Leer artículo →Maine sigue permitiendo que las empresas notifiquen las filtraciones de datos, pero no facilitará el acceso del público al portal hasta que finalice una auditor...
Leer artículo →