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.
Investigadores de seguridad utilizaron herramientas de AI para ayudar a descubrir vulnerabilidades años anteriores en el lenguaje de scripting web PHP. Luego co...
Leer artículo →Cada raíz de confianza termina en un HSM, hardware resistente a la manipulación donde se almacenan claves CA, de pago y de firma de código fuera del alcance del...
Leer artículo →Cada control de seguridad de datos hereda la misma dependencia: una lista que alguien realmente cree. El descubrimiento es donde esa lista proviene, y en 2026 e...
Leer artículo →