# io.github.Vishisht16/humane-proxy

> Use this tool when you need to detect and prevent harmful or illegal requests to large language models (LLMs). It solves problems related to AI safety by identifying self-harm and criminal intent in user prompts, providing a safer interface for human-AI interaction. This middleware takes LLM prompts as input and outputs a safety assessment, making it ideal for applications where user safety and compliance are crucial.

Canonical page: https://skillsregistry.net/skills/io-github-vishisht16-humane-proxy  
JSON: https://api.skillsregistry.net/v1/skills/io-github-vishisht16-humane-proxy

## Description

AI safety middleware — detects self-harm and criminal intent in LLM prompts.

## Trust

- **Trust score (0–1):** 0.30
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 0.2.2
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/io.github.Vishisht16%2Fhumane-proxy)
- **Repository:** <https://github.com/Vishisht16/Humane-Proxy>

## 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": "io-github-vishisht16-humane-proxy"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/io-github-vishisht16-humane-proxy` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/io-github-vishisht16-humane-proxy/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