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.
Operadores de ransomware explotan un fallo en la VPN GlobalProtect de Palo Alto Networks para bypassar el multi-factor authentication y entrar en las redes corp...
Leer artículo →La empresa fintech Revolut trabaja para resolver una gran desconexión que interrumpió la mayoría de sus servicios en todo el mundo esta mañana.
Leer artículo →Ahold Delhaize, uno de los mayores grupos de retail alimenticio del mundo, confirmó que el ataque cibernético ocurrido la semana pasada interrumpió servicios en...
Leer artículo →