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 proyecto Apache Kafka reveló 12 vulnerabilidades. La más grave, CVE-2026-110985, permite a un atacante no autenticado falsificar un token de inicio de sesión...
Leer artículo →Los atacantes han explotado la vulnerabilidad CVE-2026-116779, una vulnerabilidad crítica de FreeSWITCH que permite ejecutar comandos del servidor mediante un ú...
Leer artículo →Las campañas públicas de Jess Asato en favor de las víctimas del abuso en línea la pusieron en el alcance del escándalo de deepfake de Grok. Luego, la miembro d...
Leer artículo →