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.
IBM ha superado a TSMC, Intel y Samsung al crear un chip de 0,7 nm con 100.000 millones de transistores para IA, rompiendo la barrera del nanómetro mediante un...
Leer artículo →El Foro Económico Mundial sostiene que la IA podría reemplazar a los programadores antes que a los camioneros debido a que los datos de entrenamiento son más ac...
Leer artículo →La campaña de robo de credenciales FortiBleed, que ha comprometido más de 430.000 firewalls FortiGate en todo el mundo, alimenta directamente dos operaciones ac...
Leer artículo →