# SkillsSafe

> Use this tool when you need to secure your system from potential threats in SKILL.md files, MCP configs, and system prompts. SkillsSafe scans for various security risks, including credential theft and data exfiltration, and provides risk scores with severity ratings. It offers a convenient interface through SSE endpoint, npm package, and REST API, allowing for easy integration and risk assessment without requiring signup.

Canonical page: https://skillsregistry.net/skills/gucci-atlasv-skillssafe  
JSON: https://api.skillsregistry.net/v1/skills/gucci-atlasv-skillssafe

## Description

Scans SKILL.md files, MCP configs, and system prompts for security threats before installation. Detects credential theft, data exfiltration, prompt injection, shell injection, zero-width character attacks, scope creep, and memory poisoning. Returns risk scores with severity ratings and shareable report links. Available via SSE endpoint, npm package, and REST API with no signup required.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/gucci-atlasv-skillssafe)
- **Repository:** <https://github.com/gucci-atlasv/skillssafe.com>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "gucci-atlasv-skillssafe"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/gucci-atlasv-skillssafe` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/gucci-atlasv-skillssafe/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt