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.
Un atacante utilizó contraseñas robadas de empleados de la administración tributaria francesa para sustraer datos fiscales de cientos de miles de contribuyentes...
Leer artículo →Investigadores de ciberseguridad han identificado un conjunto de 101 paquetes npm utilizados para atraer a desarrolladores a una campaña de suscripción a grupos...
Leer artículo →Investigadores de ANY.RUN rastrearon una campaña de phishing dirigida a CSuite en EE. UU. a través de 351 análisis en entornos aislados, con un 51 % de los enví...
Leer artículo →