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.
Más de 24.000 servidores expuestos a internet están filtrando hashes de contraseñas de autenticación debido a una vulnerabilidad de hace 20 años en su interfaz...
Leer artículo →Dysphoria, una línea de botnets de Internet de las Cosas (IoT) rastreada por CNCERT y XLab, ha adoptado servicios de nombre basados en blockchain y retransmisio...
Leer artículo →El CEO de OpenAI, Sam Altman, ha declarado que la inteligencia artificial ha entrado en la singularidad largamente teorizada, una etapa fundamental en la que lo...
Leer artículo →