# SkillsSafe

SkillsSafe is a specialized security scanner designed for the AI Agent era. As agents gain more autonomy (executing code, managing files), the risk of malicious "skills" increases. SkillsSafe allows …

## Quick Start

```bash
# Connect this server (installs CLI if needed)
npx -y @smithery/cli@latest mcp add gucci/SkillsSafe

# Browse available tools
npx -y @smithery/cli@latest tool list gucci/SkillsSafe

# Get full schema for a tool
npx -y @smithery/cli@latest tool get gucci/SkillsSafe scan_skill

# Call a tool
npx -y @smithery/cli@latest tool call gucci/SkillsSafe scan_skill '{}'
```

## Direct MCP Connection

Endpoint: `https://skillssafe--gucci.run.tools`

## Tools (2)

- `scan_skill` — Scan an AI agent skill file (SKILL.md, MCP tool config, or system_prompt) for security threats before installation. Det…
- `get_report` — Retrieve a previously generated scan report by scan_id. Returns a link to the full report page at skillssafe.com.

```bash
# Get full input/output schema for a tool
npx -y @smithery/cli@latest tool get gucci/SkillsSafe <tool-name>
```

## Prompts (2)

- `scan_before_install` (skill_url) — Prompt template to scan an AI agent skill or MCP tool before installing it. Guides the model to use SkillsSafe to verif…
- `review_skill_content` (skill_content) — Prompt template to review raw skill content pasted by the user and produce a security assessment.