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.
Symantec afirma que los atacantes también utilizaron AnyDesk, PsExec y un conjunto de herramientas para la obtención de credenciales basado en NirSoft en un ata...
Leer artículo →Una bandeja de entrada de correo electrónico comprometida puede convertirse en un arma para la ejecución remota de código en el equipo de la víctima, no mediant...
Leer artículo →Un nuevo ataque de tipo "Fuego amigo" oculta instrucciones en el archivo README de un repositorio. Basta con pedirle al agente que revise parte del có...
Leer artículo →