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.
AWS publicó dos boletines de seguridad el 2 de octubre de 2026, que cubren cuatro vulnerabilidades (CVE). Tres afectan a Loom para AWS, una plataforma de agente...
Leer artículo →La Fundación Apache Software reveló ocho vulnerabilidades (CVE) el 2 de octubre de 2026, distribuidas en tres proyectos. La más urgente es la vulnerabilidad CVE...
Leer artículo →Un programador creó una "cámara de tortura" para provocar respuestas de angustia en modelos de IA, generando un debate sobre el bienestar de la inteli...
Leer artículo →