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.
Se ha detectado un cambio estructural significativo en el panorama de las botnets. Investigadores de seguridad de XLab han descubierto NadMesh, una botnet basad...
Leer artículo →Anthropic anunció recientemente un cambio importante en sus modelos avanzados de IA. A partir del 20 de julio de 2026, la compañía adoptará un modelo de acceso...
Leer artículo →Los clientes de AWS en todo el mundo se alarmaron cuando la Consola de facturación y administración de costos de AWS y el Explorador de costos comenzaron a most...
Leer artículo →