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.
Motor de pruebas de penetración con IA autónoma, seguridad ofensiva continua en web, nube, Active Directory y Kubernetes. El razonamiento agente y la ejecución...
Leer artículo →El gigante de servicios de TI Accenture confirmó haber sufrido una brecha de seguridad después de que un ciberdelincuente afirmara haber robado 35 GB de código...
Leer artículo →Ubiquiti ha publicado actualizaciones de seguridad para corregir siete vulnerabilidades críticas en UniFi OS, incluyendo una vulnerabilidad de máxima gravedad i...
Leer artículo →