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.
HEAVYGRAM es una puerta trasera de vigilancia para Windows que convierte a Telegram en un centro de mando operativo para los atacantes. En lugar de depender de...
Leer artículo →El código malicioso que se ejecuta dentro de una máquina virtual de Docker Sandboxes en macOS podría escapar del directorio del proyecto compartido con ella y l...
Leer artículo →La CISA ha instado a las organizaciones a implementar credenciales, sistemas, archivos y activos de datos falsos dentro de sus entornos para exponer a los ataca...
Leer artículo →