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.
Según VulnCheck, una vulnerabilidad crítica que afecta al servidor de archivos HTTP (HFS) de Rejetto está siendo objeto de intentos de explotación. La vulnerabi...
Leer artículo →Una función poco conocida de la base de datos de Safari podría proporcionar a los investigadores forenses digitales una nueva forma de analizar la actividad de...
Leer artículo →Google ha suspendido temporalmente la recepción de informes para su Programa de Recompensas por Vulnerabilidades de Software de Código Abierto (OSS VRP) tras re...
Leer artículo →