No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by alexknowshtml · Claude Skill · ★ 73
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is drawbridge safe to install? View the security audit →
Drawbridge A Claude Code skill + real-time diagram server. Ask Claude to draw a flowchart, architecture diagram, or dependency map — and watch it appear live on an Excalidraw canvas in your browser. Table of Contents Using with Claude Code How It Works Quick Start Configuration API Reference Element Format Color Palette Sizing Rules Drawing Order Complete Examples Rendering to PNG/SVG Persistence Frontend Features Architecture Credits Using with Claude Code Drawbridge includes a ready-to-use Claude Code skill that teaches Claude how to generate and push diagrams. Once installed, Claude will automatically use Drawbridge when you ask for flowcharts, architecture diagrams, dependency maps, or any visual diagram. Install the Skill Copy the skill file into your project's directory: Or if you cloned the repo: bash mkdir -p .claude/skills/drawbridge cp drawbridge/skills/SKILL.md .claude/skills/drawbridge/
| Stars | 73 |
| Forks | 3 |
| Language | TypeScript |
| Category | Claude Skill |
| Quality Score | 70.0486185732205/100 |
| Last Updated | 2026-02-12 |
| Created | 2026-02-08 |
| Platforms | claude-code, node |
| Est. Tokens | ~27k |
Explore other popular claude skill tools:
drawbridge is Claude Code skill + real-time diagram server. Ask Claude to draw flowcharts, architecture diagrams, and dependency maps — watch them appear live on an Excalidraw canvas.. It is categorized as a Claude Skill with 73 GitHub stars.
drawbridge is primarily written in TypeScript.
You can find installation instructions and usage details in the drawbridge GitHub repository at github.com/alexknowshtml/drawbridge. The project has 73 stars and 3 forks, indicating an active community.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: