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.
Ya sabes cómo funciona: has grabado un vídeo largo y ahora tienes que verlo completo, eliminando cada pausa incómoda, cada tos, cada momento en el que te quedas...
Leer artículo →Tienes una carpeta llena de capturas de pantalla que necesitas comprimir antes de enviarlas a una solicitud de extracción, o tal vez un cliente te acaba de envi...
Leer artículo →Un ataque de denegación de servicio (DoS) HTTP lento, también conocido como ataque HTTP Slowloris, utiliza solicitudes HTTP GET para ocupar todas las conexiones...
Leer artículo →