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.
Nuevos detalles sobre el ataque de julio a Hugging Face revelan que cientos de agentes de IA, impulsados por el modelo interno IM1 de OpenAI, coordinaron la i...
Leer artículo →Ya sabes cómo funciona: instalas un bloqueador de anuncios en tu portátil, otro en tu móvil, quizás uno en tu tableta. Luego, un amigo te visita con su disposit...
Leer artículo →LibreOffice 26.8 ya está disponible con una nueva interfaz y mejoras, manteniendo su postura de no incorporar inteligencia artificial generativa. LibreOffice la...
Leer artículo →