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 kits de phishing ya no se limitan a copiar una página de inicio de sesión conocida y esperar a que la víctima introduzca sus credenciales. Los atacantes inc...
Leer artículo →Double Counter, un bot de seguridad para Discord, reveló una brecha de seguridad que expuso datos de usuarios después de que un atacante accediera a sus sistema...
Leer artículo →Investigadores de ciberseguridad han descubierto un grupo de 16 extensiones maliciosas para Mozilla Firefox capaces de robar frases de recuperación y claves pri...
Leer artículo →