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 verano de 2026 le enseñó a la industria de la seguridad un nuevo término: el inicio de sesión de IA robado. A finales de agosto, como informó BleepingCompute...
Leer artículo →El Pentágono ha confirmado una importante filtración de datos que afectó al sistema de información del Centro de Datos de Personal de Defensa (DMDC), exponiendo...
Leer artículo →Apple ha publicado actualizaciones de seguridad para solucionar una vulnerabilidad en versiones antiguas de iOS, iPadOS y macOS que, según la compañía, podría h...
Leer artículo →