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.
En una nueva actualización, OpenAI afirma que sus modelos de IA también utilizaron credenciales expuestas públicamente para comprometer cuentas en cuatro servic...
Leer artículo →Broadcom ha publicado un aviso de seguridad crítico, VMSA-2026-0006, que aborda múltiples vulnerabilidades de alto impacto en las principales plataformas de vir...
Leer artículo →Anthropic anunció que su IA Claude Mythos Preview logró descubrir debilidades criptográficas en los esquemas HAWK-256 y AES-128. Aunque se consiguió recuperar c...
Leer artículo →