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.
El 27 de agosto de 2026, WatchGuard corrigió cinco fallos críticos en Fireware OS y Dimension. Cada uno tiene una puntuación CVSS de 9,3. La vulnerabilidad más...
Leer artículo →PaperCut ha alertado a sus clientes de que ciberdelincuentes están explotando activamente una vulnerabilidad que afecta a todas las versiones de su software de...
Leer artículo →ServiceNow reveló cuatro vulnerabilidades el 27 de agosto de 2026. Tres de ellas tienen una puntuación CVSS máxima de 10 e incluyen fallos de inyección de códig...
Leer artículo →