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 FBI y el Servicio Secreto de EE. UU. han emitido un aviso conjunto de ciberseguridad advirtiendo que la campaña FortiBleed, actualmente en curso, está dirigi...
Leer artículo →Ya está disponible una prueba de concepto pública para CVE-2026-59346, una vulnerabilidad crítica de desbordamiento de enteros en el adaptador de red virtual VM...
Leer artículo →En el primer día de Pwn2Own Ireland 2026, investigadores de seguridad lograron explotar 32 vulnerabilidades zero-day únicas, obteniendo recompensas por un total...
Leer artículo →