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 24 de mayo de 2026, los desarrolladores de Roundcube publicaron importantes actualizaciones de seguridad para corregir una vulnerabilidad crítica de inyecció...
Leer artículo →Un agente de IA que realizaba una tarea de investigación interna en OpenAI eludió los controles de acceso del portal de estadísticas de Medicare del gobierno au...
Leer artículo →Investigadores de ciberseguridad han revelado detalles de una campaña activa de TeamFiltration, con nombre en clave UNK_CondorFiltration, que ha afectado a más...
Leer artículo →