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 el Centro de Coordinación JPCERT (JPCERT/CC), los atacantes responsables de una serie de filtraciones de datos personales en organizaciones japonesas abus...
Leer artículo →El FBI y el Departamento de Justicia de EE. UU. han incautado siete dominios vinculados a Microscan y FishHub, dos herramientas de hacking presuntamente operada...
Leer artículo →Más de 17.000 repositorios falsos en GitHub están distribuyendo el malware SmartLoader tras la reactivación de la campaña FakeGit a principios de este mes para...
Leer artículo →