Installs into .claude/skills of the current project.
Are you the author of Scan Claude Code Configs For Secrets Permission Drift And Unsafe Mcp Hookups With Agentshield?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/agentskillexchange-scan-claude-code-configs-for-secrets-permission-dr)
---
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/)
