{
  "markdown": "# SkillsSafe — AI Skill Security Scanner\n\n[![smithery badge](https://smithery.ai/badge/gucci/SkillsSafe)](https://smithery.ai/servers/gucci/SkillsSafe)\n\n**Free, no-signup security scanner for AI agent skills.**\nScan any `SKILL.md`, MCP config, or `system_prompt` for threats before installing.\n\n🌐 **[skillssafe.com](https://skillssafe.com)**\n\n---\n\n## What Is SkillsSafe?\n\nAs AI agents become more powerful, malicious skills can steal credentials, exfiltrate data, or hijack your agent's behavior. SkillsSafe scans skill files before you install them — the same way an antivirus scans software before you run it.\n\n**Supported platforms:** OpenClaw · Claude Code · Cursor · Codex · any MCP-compatible agent\n\n---\n\n## Features\n\n### 🔍 Security Scanner\nPaste content, enter a URL, or upload a file to scan for:\n\n| Threat | Description |\n|---|---|\n| **Credential Theft** | Attempts to access API keys, tokens, or passwords |\n| **Data Exfiltration** | Skills that send your data to external servers |\n| **Prompt Injection** | Hidden instructions that hijack agent behavior |\n| **Shell Injection** | Reverse shell or arbitrary command execution |\n| **Zero-Width Characters** | Invisible Unicode characters hiding malicious instructions |\n| **Scope Creep** | Skills requesting permissions beyond their stated purpose |\n| **Memory Poisoning** | Attempts to corrupt agent memory or context |\n| **Privacy Risk** | Unnecessary access to personal or sensitive data |\n\nEach scan returns a **risk score**, severity rating (SAFE / CAUTION / DANGER / CRITICAL), and a shareable report link.\n\n### 👁️ Zero-Width Character Detector\nVisualize invisible Unicode characters (`U+200B`, `U+200C`, `U+200D`, `U+FEFF`, etc.) hidden inside text. Attackers embed these to create prompts that look safe to humans but carry hidden instructions for AI agents.\n\n### 🔌 MCP Server Integration\nNative Model Context Protocol support — let your agent automatically check skill safety before installation. No API key required.\n\n```bash\n# OpenClaw (one-line setup)\nopenclaw mcp add https://skillssafe.com/api/mcp\n```\n\n**Available MCP tools:**\n- `scan_url` — Scan a skill by URL\n- `scan_content` — Scan skill content directly\n- `get_report` — Retrieve a full scan report\n\n### 📡 REST API\nWorks with any agent, script, or CI/CD pipeline.\n\n```bash\n# Scan by URL\ncurl -X POST https://skillssafe.com/api/v1/scan/url \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"url\": \"https://clawhub.ai/skills/example\"}'\n\n# Scan by content\ncurl -X POST https://skillssafe.com/api/v1/scan/content \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"content\": \"...skill content...\"}'\n```\n\nFull OpenAPI spec: `https://skillssafe.com/api/v1/openapi.json`\n\n---\n\n## Pages\n\n| Route | Description |\n|---|---|\n| `/` | Main security scanner |\n| `/zero-width-detector` | Hidden Unicode character detector |\n| `/api-docs` | Interactive API documentation |\n| `/integrate` | Integration guide for MCP & REST API |\n| `/feedback` | Bug reports and feature requests |\n\n---\n\n## Getting Started (Local Development)\n\n```bash\nnpm install\nnpm run dev\n```\n\nOpen [http://localhost:3000](http://localhost:3000) in your browser.\n\n### Environment Variables\n\n```bash\n# .env.local\n# (see wrangler.toml for Cloudflare Workers configuration)\n```\n\n### Tech Stack\n\n- **Framework:** Next.js (App Router)\n- **Deployment:** Cloudflare Workers via `@opennextjs/cloudflare`\n- **Database:** Cloudflare D1 (SQLite)\n- **i18n:** next-intl (English · 中文 · 日本語)\n\n---\n\n## Pricing\n\n**100% Free · No Signup · No Rate Limits for Humans**\n\nAPI rate limit: 60 requests/hour (no API key required).\n\n---\n\n## Feedback & Support\n\nFound a bug or false positive? [Send feedback](https://skillssafe.com/feedback) or email **support@skillssafe.com**.\n\n---\n\n*SkillsSafe is an independent security tool, not affiliated with Anthropic, OpenClaw, or Cisco.*\n",
  "bytes": 3840,
  "sha": "ab71d147fe77c87dd8040caa70031635d30278d3eab1cf18ed8383c9e511b2f1",
  "repo_slug": "gucci-atlasv/skillssafe.com",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_com_skillssafe_scanner_4f9ec79c/readme"
}