# mirage-proxy

> mirage-proxy — chandika-mirage-proxy. Use this tool when you need to protect sensitive data in OpenClaw LLM API calls by filtering out personally identifiable information (PII) and secrets. The mirage-proxy tool installs and configures a transparent filter, taking in API requests and returning filtered responses to prevent data exposure. Ideal for use cases requiring secure and compliant handling of sensitive information in AI workflows.

Canonical page: https://skillsregistry.net/skills/chandika-mirage-proxy  
JSON: https://api.skillsregistry.net/v1/skills/chandika-mirage-proxy

## Description

Install and configure mirage-proxy as a transparent PII/secrets filter for OpenClaw LLM API calls.

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** instructions
- **Runtime environment:** llm
- **Category:** ai-ml
- **Updated:** 2026-09-19

## Source

- **Source listing:** [ClawHub](https://clawskills.sh/skills/chandika-mirage-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": "chandika-mirage-proxy"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/chandika-mirage-proxy` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/chandika-mirage-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