skills.rest
Zenobia000
Zenobia000COMMUNITY
Explore all skills by this author →
WebsiteGitHub

security-scan

Audit Claude Code configuration files for security vulnerabilities and misconfigurations.

2|Updated Apr 7, 2026
Search Tags:#devsecops#claude-code#configuration-audit#security-scan#prompt-injection#vulnerability-scan#agentshield
One-click install
npx skills add https://github.com/Zenobia000/ai-brainstorming --skill security-scan-zenobia000
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: security-scan
Source: https://github.com/Zenobia000/ai-brainstorming/tree/main/.claude/custom-rule%26skill/skills/security-scan
Command: npx skills add https://github.com/Zenobia000/ai-brainstorming --skill security-scan-zenobia000

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Unsecure Claude Code configurations can expose projects to data breaches, prompt injection attacks, and unauthorized access via hardcoded secrets, overly permissive permissions, or vulnerable MCP server setups. This Skill eliminates the manual effort of reviewing every configuration file for these high-impact risks.

Core Features & Use Cases

  • Comprehensive Config Scanning: Checks CLAUDE.md, settings.json, MCP configs, hooks, and agent definitions for hardcoded secrets, prompt injection patterns, and permission misconfigurations.
  • Actionable Severity Grading: Categorizes findings by criticality (A to F grade) to help prioritize fixes for the most urgent risks first.
  • Use Case: Before pushing Claude Code configuration changes to a shared repository, run this scan to catch exposed API keys or unrestricted shell access that could compromise project or team data.

Quick Start

Use the security-scan skill to audit the current project's .claude/ directory for security vulnerabilities and generate a severity-graded report.

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?▼

To scan Claude Code configurations for security vulnerabilities, audit the `.claude/` directory to detect hardcoded secrets, prompt injection patterns, and permission misconfigurations across CLAUDE.md, settings.json, and MCP server configs.

What security risks are found in Claude Code settings.json and MCP server configs?▼

Risks found in Claude Code settings.json and MCP server configs include hardcoded secrets, overly permissive permissions granting unrestricted shell access, and command injection vectors vulnerable to prompt injection attacks.

Do I need AgentShield to audit Claude Code configurations for prompt injection risks?▼

Yes, the AgentShield tool is required to audit Claude Code configurations, as it provides the scanning engine required to detect prompt injection patterns, misconfigurations, and exposed secrets in agent definition files.

When should I run a security scan on my Claude Code project setup?▼

Run a security scan on your Claude Code project setup during new repository onboarding, pre-commit configuration validation, and periodic security hygiene workflows to catch exposed API keys before pushing changes.

How does severity grading work for Claude Code configuration security findings?▼

Severity grading for Claude Code configuration security findings works by categorizing detected vulnerabilities on an A to F scale, helping prioritize fixes for the most urgent risks like exposed secrets and unrestricted permissions.

Can I check Claude Code hooks and agent definitions for command injection vectors?▼

Yes, you can check Claude Code hooks and agent definition files for command injection vectors by running a configuration audit that scans these files for malicious patterns and vulnerable MCP server setups.

Related Skills

Explore More Software Engineering Skills→
himanshu231204himanshu231204
2

security-scan

Scan Claude Code configuration directories for security vulnerabilities and misconfigurations.

Community
Intermediate
luongldptitluongldptit

security-scan

Scans Claude Code configs for vulnerabilities and outputs severity-graded reports.

Community
Intermediate
Sumeet138Sumeet138
1

block-no-verify-hook

Block git bypass flags with a PreToolUse hook in .claude/settings.json.

Community
Intermediate
jiten-singh-shahijiten-singh-shahi
13

security-scan

Audit Claude Code configuration files for security vulnerabilities and emit JSON findings.

Community
Intermediate