# skill-firewall

> skill-firewall — mkhaytman87-skill-firewall. Use this tool when you need to protect against malicious input and prevent unauthorized access to sensitive information. The skill-firewall provides a security layer that blocks prompt injection from external skills, solving problems related to data breaches and cyber attacks. It takes in external skill requests as input and outputs sanitized prompts, making it ideal for use in high-stakes applications where security is paramount.

Canonical page: https://skillsregistry.net/skills/mkhaytman87-skill-firewall  
JSON: https://api.skillsregistry.net/v1/skills/mkhaytman87-skill-firewall

## Description

Security layer that prevents prompt injection from external skills.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** instructions
- **Runtime environment:** llm
- **Category:** ai-ml
- **Updated:** 2026-09-13

## Source

- **Source listing:** [ClawHub](https://clawskills.sh/skills/mkhaytman87-skill-firewall)

## 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": "mkhaytman87-skill-firewall"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/mkhaytman87-skill-firewall` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/mkhaytman87-skill-firewall/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