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.
Cinco versiones maliciosas de paquetes AsyncAPI fueron publicadas en el Gestor de Paquetes de Node (npm) en un ataque a la cadena de suministro que distribuyó u...
Leer artículo →Recientemente, un usuario informó en X que unos hackers habían comprometido su cuenta de Microsoft. Tras detectar la anomalía, Microsoft respondió bloqueando la...
Leer artículo →OpenAI finalmente ha lanzado su primer producto de hardware. Sin embargo, no se trata del sofisticado altavoz inteligente que muchos expertos habían anticipado....
Leer artículo →