# cleaner-code

> cleaner-code — goldmembrane-cleaner-code. Use this tool when you need to detect and prevent malicious code attacks in AI-generated code, such as invisible Unicode, Trojan Source, and dependency attacks. It analyzes code locally using static analysis and CodeBERT deep learning, providing a secure scanning solution for developers. Ideal for use with git, it helps identify potential security threats before they compromise your project.

Canonical page: https://skillsregistry.net/skills/goldmembrane-cleaner-code  
JSON: https://api.skillsregistry.net/v1/skills/goldmembrane-cleaner-code

## Description

AI code security scanner MCP server — detects invisible Unicode, Trojan Source, homoglyphs, Glassworm steganography, rules file backdoors, and dependency attacks in AI-generated code. Static analysis + CodeBERT deep learning. Runs locally.

## Trust

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

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** security
- **Updated:** 2026-09-20

## Source

- **Source listing:** [GitHub](https://github.com/goldmembrane/cleaner-code)

## 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": "goldmembrane-cleaner-code"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/goldmembrane-cleaner-code` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/goldmembrane-cleaner-code/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