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.
El investigador de seguridad Olivier Laflamme ha revelado dos cadenas independientes de ejecución remota de código (RCE) con privilegios de root que afectan al...
Leer artículo →Windows XP ha cumplido esta semana 25 años desde el lanzamiento de la versión RTM para fabricantes OEM. Un aniversario redondo para un sistema operativo que ha...
Leer artículo →Cosmos Labs ha advertido que una vulnerabilidad crítica en el manejo de saldos del módulo compartido Cosmos EVM fue explotada para sustraer fondos de seis block...
Leer artículo →