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.
Microsoft Maia 300 utiliza TSMC N2P y HBM4 para escalar la inferencia de inteligencia artificial a niveles multi-gigawatt hasta 2027, reduciendo la dependencia...
Leer artículo →Un reciente ataque cibernético a TFG London interrumpió los sistemas de TI y los pedidos online de las marcas de moda británicas Phase Eight, Hobbs y Whistles d...
Leer artículo →Palo Alto Networks cerró la vulnerabilidad de código CVE-2026-0322, conocida como Zero-Day, que fue explotada en ataques limitados para lograr ejecución de códi...
Leer artículo →