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.
Microsoft afirma que malinterpretó un bug causante de problemas de conexión de red Always On VPN como solucionado en las actualizaciones acumulativas de Windows...
Leer artículo →Un investigador descubrió que los atacantes tomaron control de más de 300 relay de salida de Tor en octubre temprano y utilizaron estos para redirigir las conex...
Leer artículo →Un equipo de AppSec puede dirigir un agente de inteligencia artificial ejecutándose en un modelo general a sus propios aplicativos web con poco configurado. Cla...
Leer artículo →