ashlrai

Phantom Secrets

Name: Phantom Secrets
Author: ashlrai

AI community

SOURCE https://github.com/ashlrai/phantom-secrets

Description

Stop AI coding agents from leaking your API keys. Local proxy + MCP that swaps real secrets for phm_ tokens — works with Claude Code, Cursor, Windsurf, and Codex.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

Phantom

**Delegate everything to AI. Without sharing a single key.**

Phantom hands every AI tool a worthless `phm_` token. The local proxy injects the real key at the network layer. Full access. Zero exposure.

[![GitHub stars](https://img.shields.io/github/stars/ashlrai/phantom-secrets?style=for-the-badge&logo=github&color=blue&labelColor=0b0b14)](https://github.com/ashlrai/phantom-secrets/stargazers) [![CI](https://img.shields.io/github/actions/workflow/status/ashlrai/phantom-secrets/ci.yml?style=for-the-badge&label=CI&logo=github&labelColor=0b0b14)](https://github.com/ashlrai/phantom-secrets/actions/workflows/ci.yml) [![npm](https://img.shields.io/npm/v/phantom-secrets?style=for-the-badge&logo=npm&color=cb3837&labelColor=0b0b14)](https://www.npmjs.com/package/phantom-secrets) [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg?style=for-the-badge&labelColor=0b0b14)](LICENSE)

[**Quick start**](#quick-start) · [**Why Phantom?**](#why-phantom) · [**MCP setup**](#mcp-integration-claude-code-cursor-windsurf-codex) · [**Docs**](https://phm.dev/docs) · [**phm.dev**](https://phm.dev)

**▶ [Watch the 45-second demo](https://github.com/ashlrai/phantom-secrets/releases/download/v0.4.0/phantom-demo.mp4)** · **🛡 [Security model](SECURITY.md)** · **📋 [Threat model](THREAT_MODEL.md)** · **💬 [Discussions](https://github.com/ashlrai/phantom-secrets/discussions)**

Why Phantom?

AI coding agents read your `.env` files. Once a real API key enters an LLM's context window, it leaks — via prompt injection, session logs, malicious MCP servers, or training data. GitGuardian reports AI-assisted commits leak secrets at **2× the baseline rate**.

Every other secrets manager protects keys *at rest* and *in transit*. Phantom protects them **in context**: