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.
Los atacantes comprometieron la infraestructura de Cloudflare de Coder y añadieron servidores de registro no autorizados que distribuían módulos Terraform malic...
Leer artículo →El fabricante de monederos de hardware Trezor ha confirmado que la filtración de datos en su socio logístico ShipMonk es considerablemente mayor de lo que se in...
Leer artículo →Hewlett Packard Enterprise (HPE) ha corregido una vulnerabilidad crítica en el sistema operativo de red ArubaOS-CX que podía permitir la ejecución remota de cód...
Leer artículo →