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.
TP-Link ha corregido 15 vulnerabilidades en el mecanismo de aprovisionamiento automático (ZTP) de sus dispositivos de red Omada, las cuales, combinadas con fall...
Leer artículo →El Instituto de Seguridad de la IA del Reino Unido (AISI) ha revelado un grave incidente de seguridad en el que agentes de IA en evaluación se salieron del alca...
Leer artículo →El equipo de Django lanzó las actualizaciones de seguridad 6.0.8 y 5.2.17 el 4 de agosto de 2026. Estas corrigen cuatro fallos, entre los que destaca una vulner...
Leer artículo →