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 agente de IA autónomo JadePuffer se ha actualizado con un malware personalizado llamado EncForge, que se centra en el cifrado de activos de IA, como conjunto...
Leer artículo →Investigadores de ciberseguridad han descubierto cerca de 7600 repositorios maliciosos de GitHub, de los cuales más de 800 se hacen pasar por servidores de inte...
Leer artículo →Durante junio de 2026, Arctic Wolf Labs rastreó varias intrusiones de ransomware hasta un único punto de entrada. Los atacantes explotaron una vulnerabilidad en...
Leer artículo →