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.
Una vulnerabilidad crítica en Nuxt DevTools permite a un atacante ejecutar comandos arbitrarios en el equipo de un desarrollador. Identificada como CVE-2026-713...
Leer artículo →Una vulnerabilidad de omisión de autenticación en el proceso de inicio de sesión de Check Point SmartConsole permite a un atacante remoto no autenticado obtener...
Leer artículo →GitLab lanzó una nueva actualización el 12 de agosto de 2026. Las versiones 19.2.2, 19.1.4 y 19.0.6 corrigen 13 vulnerabilidades de seguridad en las ediciones C...
Leer artículo →