bruc3van/agent-skills-guard

What it solves

Agent Skills Guard provides a visual, secure way to manage "skills" (plugins/extensions) for AI coding agents like Claude Code. It eliminates the need to manually search GitHub, read raw code for security risks, and manage files via the command line, transforming the process into an app-store-like experience.

How it works

The tool acts as a management layer that integrates discovery, installation, and security auditing. It uses a multi-layer scanning pipeline engine to analyze skill code for risks such as remote code execution, command injection, and sensitive data leaks before installation. It also provides a GUI for browsing curated skill repositories, updating plugins, and syncing installed skills across different AI programming tools (e.g., Claude Code, Codex, Antigravity).

Who it’s for

Developers using AI coding agents who want to expand their agent's capabilities with community-created skills but are concerned about the security of executing third-party code on their local machines.

Highlights

• Multi-layer Security Scanning: Detects 8+ risk categories, including Unicode deception, multi-step attack chains, and file type masquerading.
• Hard-Trigger Protection: Automatically blocks the installation of skills that trigger critical "red line" rules (e.g., rm -rf /).
• Visual Skill Market: A curated marketplace for discovering and installing high-quality AI agent skills.
• CLI Tool Management: Automatically discovers and manages local command-line tools installed via npm, pip, Homebrew, and other package managers.
• Cross-Tool Sync: One-click synchronization of installed skills to multiple AI programming environments.