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.
Apple solicita a un tribunal frenar el desarrollo de dispositivos de OpenAI tras acusar a ex empleados de filtrar información confidencial.
Leer artículo →Jenkins corrigió una vulnerabilidad crítica, CVE-2026-70426, que eludía el filtro de deserialización JEP-200. Los atacantes con permisos de Agente/Conexión podí...
Leer artículo →Una campaña de phishing está explotando los temores en torno a la vulnerabilidad de la billetera COLDCARD, recientemente descubierta, y el presunto robo de 88,6...
Leer artículo →