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.
El miércoles por la noche tarde, el capítulo de Toronto de Crimen Stoppers rompió filas con la asociación nacional, revelando un cronograma que mostraba lo que...
Leer artículo →Los hackers en todo el mundo están apostando todo a utilizar IA agente para llevar a cabo ataques y manipulando herramientas como Claude de Anthropic para ayuda...
Leer artículo →La Fundación PHP ha revelado dos vulnerabilidades serias que podrían afectar a millones de sitios web. Los expertos en seguridad advierten que la falta de parch...
Leer artículo →