mirage-proxy
chandika 제작
Web & Frontend Development요약
Install and configure mirage-proxy as a transparent PII/secrets filter for OpenClaw LLM API calls.
설명
이 스킬이 하는 일
mirage-proxy sits between OpenClaw and LLM providers, intercepting API calls to redact secrets and PII before they reach the model. It replaces sensitive values with plausible fakes so the LLM processes realistic-looking but sanitized data. A bundled setup script handles binary download, proxy startup, and provider config patching.
Unlike per-agent prompt sanitization, mirage-proxy intercepts all LLM traffic at the network layer without requiring changes to any agent code.
사용 시점
- Reviewing codebases that contain hardcoded API keys or credentials
- Feeding customer records to an LLM without exposing real names or emails
- Debugging agent prompts that pull values from environment variables
- Comparing filtered vs unfiltered model responses side-by-side using model aliases
- Running compliance-sensitive workflows where secrets must not leave the system unredacted
예시 워크플로
User asks an agent to review a .env file containing AWS access keys
- 1
Agent sends file contents in a prompt routed through the mirage-anthropic provider
- 2
Proxy intercepts the outbound request and detects the AWS Access Key pattern
- 3
Proxy replaces the real key with a plausible fake before forwarding to Anthropic
- 4
LLM receives and processes the sanitized prompt
- 5
Agent returns the response; real credentials were never transmitted
LLM analysis of the config file with no real secrets exposed in transit
설치
clawhub install chandika/mirage-proxyCLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.