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.
La inteligencia artificial ha llegado a uno de los ámbitos más conservadores del desarrollo de software, y la disputa se ha convertido rápidamente en un conflic...
Leer artículo →El mercado de la IA en el SOC ha evolucionado más rápido que los métodos para evaluarla. El año pasado, Gartner situó a los agentes de IA en el SOC en la etapa...
Leer artículo →Se encuentran disponibles parches no oficiales gratuitos para una vulnerabilidad de día cero de Windows recientemente descubierta que permite a los atacantes es...
Leer artículo →