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.
Un usuario de la nube que solo utilice acceso a GPU convencionales puede modificar el consumo energético de un centro de datos con la suficiente rapidez como pa...
Leer artículo →Prowler es la plataforma de seguridad en la nube de código abierto más utilizada del mundo, que automatiza la seguridad y el cumplimiento normativo en cualquier...
Leer artículo →Investigadores de Sysdig han vinculado un segundo ataque al mismo servidor de Langflow con JADEPUFFER, el operador impulsado por agentes de IA que documentaron...
Leer artículo →