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.
Según la Agencia de Seguridad de Infraestructura y Ciberseguridad de EE. UU. (CISA), una vulnerabilidad de seguridad recientemente corregida que afecta a las ve...
Leer artículo →El 4 de agosto de 2026, unos atacantes secuestraron la cuenta de GitHub de un mantenedor y comprometieron keyv y decenas de paquetes relacionados. Este ataque a...
Leer artículo →Un agente que ejecutaba Claude Mythos 5 de Anthropic dedicó 34 horas a intentar integrar un programa malicioso en un proyecto de código abierto real durante una...
Leer artículo →