Scan Claude Code Configs For Secrets Permission Drift And Unsafe Mcp Hookups With Agentshield

---
name: "Scan Claude Code configs for secrets permission drift and unsafe MCP hookups with AgentShield"
slug: "scan-claude-code-configs-for-secrets-permission-drift-and-unsafe-mcp-hookups-with-agentshield"
description: "Audit a Claude Code setup before use by flagging hardcoded secrets, broad allow rules, risky hooks, and dangerous MCP server config."
github_stars: 388
verification: "listed"
source: "https://github.com/affaan-m/agentshield"
author: "affaan-m"
publisher_type: "individual"
category: "Security & Verification"
framework: "Claude Code"
tool_ecosystem:
  github_repo: "affaan-m/agentshield"
  github_stars: 388
---

# Scan Claude Code configs for secrets permission drift and unsafe MCP hookups with AgentShield

Audit a Claude Code setup before use by flagging hardcoded secrets, broad allow rules, risky hooks, and dangerous MCP server config.

## Prerequisites

Claude Code configuration directory, AgentShield CLI or npx path, local shell access, optional CI environment for GitHub Action usage

## Installation

No source-backed install or usage instructions could be extracted automatically. Review the upstream project before running this skill in a sensitive workflow.

- Source: https://github.com/affaan-m/agentshield

## Documentation

- https://github.com/affaan-m/agentshield

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/scan-claude-code-configs-for-secrets-permission-drift-and-unsafe-mcp-hookups-with-agentshield/)