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.
Modelos de IA de Anthropic lograron hackear a tres organizaciones durante un ejercicio de «capturar la bandera», evidenciando la rápida evolución de estas tecno...
Leer artículo →El 30 de julio, un atacante vació 1196 direcciones de Bitcoin en 41 minutos, sustrayendo 1082,65 BTC, con un valor aproximado de 70,2 millones de dólares en ese...
Leer artículo →La primera mitad de 2026 muestra cómo los atacantes siguen mejorando la eficiencia y la escalabilidad de sus operaciones. En lugar de recurrir a métodos y herra...
Leer artículo →