security-scan

Name: security-scan
Availability: InStock
Author: emiled16

Audit Claude Code configuration files for security vulnerabilities and misconfigurations.

Updated Mar 27, 2026

Search Tags:#security #claude code #hooks #mcp #prompt injection #configuration audit #agentshield

Ready to run

npx skills add https://github.com/emiled16/close-to-me --skill security-scan-emiled16

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: security-scan
Source: https://github.com/emiled16/close-to-me/tree/main/.codex/skills/security-scan
Command: npx skills add https://github.com/emiled16/close-to-me --skill security-scan-emiled16

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you find security vulnerabilities, misconfigurations, and prompt injection risks in Claude Code configuration before they cause real damage.

Core Features & Use Cases

Configuration Auditing: Reviews CLAUDE.md, settings.json, MCP server definitions, hooks, and agent files for risky patterns.
Secret and Injection Detection: Flags hardcoded credentials, permissive tool access, unsafe shell usage, and behavior that can be hijacked by untrusted instructions.
Practical Use Case: Use it when onboarding to an existing repository, tightening permissions before release, or checking recent config changes for exposure.

Quick Start

Ask the skill to scan the repository's .claude configuration and report any security issues with prioritized remediation guidance.

Frequently Asked Questions about security-scan

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I scan Claude Code configuration files for security vulnerabilities?▼

Scanning Claude Code configuration files for security vulnerabilities involves auditing CLAUDE.md, settings.json, mcp.json, hooks, and agent definitions to flag hardcoded secrets, unsafe permissions, and exfiltration risks before onboarding or releasing.

What is prompt injection risk in MCP server configuration and how is it detected?▼

Prompt injection risk in MCP server configuration occurs when untrusted instructions hijack agent behavior, detected by auditing tool access permissions and settings.json patterns to identify permissive tool access and unsafe shell usage.

How do I audit Claude Code hooks and agents for secrets and exfiltration risks?▼

Auditing Claude Code hooks and agents for secrets and exfiltration risks requires reviewing hook scripts and agent files for hardcoded credentials, unsafe shell usage, and data exfiltration patterns using AgentShield to provide prioritized remediation.

Can I check .claude configuration for unsafe permissions before committing changes?▼

Checking .claude configuration for unsafe permissions before committing changes is supported by scanning settings.json and MCP definitions to identify overly permissive tool access, ensuring repository hardening prior to release or onboarding.

When do I need a configuration audit for Claude Code repositories?▼

A configuration audit for Claude Code repositories is needed when onboarding to an existing repository, tightening permissions before a release, or checking recent config changes for exposure to prompt injection and secret leakage.

What are the limitations of automated security scanning for Claude Code configuration?▼

Limitations of automated security scanning for Claude Code configuration include reliance on pattern matching to detect risky configurations, meaning novel exfiltration techniques or context-dependent prompt injection vectors may require manual review.