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.
Funcionarios de la Universidad Estatal de Michigan (MIU) informaron que las recientes denuncias de un grupo de ransomware están relacionadas con un incidente oc...
Leer artículo →La plataforma brasileña de criptomonedas Mercado Bitcoin suspendió todos los depósitos y retiros tras un incidente de ciberseguridad ocurrido el lunes por la ma...
Leer artículo →El director del Centro Nacional de Ciberseguridad (NCSC) del país advertirá el martes que Gran Bretaña se enfrenta a la "posibilidad real de un aumento sin...
Leer artículo →