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.
Según la Unidad 42 de Palo Alto Networks, un ciberdelincuente de habla china utilizó DeepSeek a través del marco de código abierto Hermes Agent para lanzar ataq...
Leer artículo →Los ciberdelincuentes se hacen pasar por personal de soporte técnico en llamadas de Microsoft Teams para obtener acceso remoto a dispositivos corporativos e imp...
Leer artículo →La empresa estadounidense de semiconductores Analog Devices anunció que una persona no autorizada accedió a algunos de sus sistemas y extrajo ciertos archivos....
Leer artículo →