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.
Investigadores de ciberseguridad alertaron sobre una brecha en la cadena de suministro que afecta a BdThemes, proveedor de plugins para WordPress, lo que llevó...
Leer artículo →El asistente de IA de un australiano se ha convertido en el centro de lo que se describe como el primer ciberataque autónomo de IA conocido en el país, tras exp...
Leer artículo →OpenAI ha anunciado la suspensión de algunas actividades internas relacionadas con su próximo modelo de inteligencia artificial (IA), Astra, tras una evaluación...
Leer artículo →