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 ha recordado a sus clientes que la solución de gestión de identidades y accesos (IAM) Entra ID contará con una mayor protección contra ataques de inye...
Leer artículo →La Agencia de Seguridad de Infraestructura y Ciberseguridad de EE. UU. (CISA) advierte sobre una nueva vulnerabilidad crítica en MikroTik RouterOS que podría pe...
Leer artículo →Según la investigación “PixelLeak” de Glow Labs, agentes de codificación de IA expusieron más de 13.000 capturas de pantalla internas de más de 300 organizacion...
Leer artículo →