skills.rest
RUSHYOP
RUSHYOPCOMMUNITY
Explore all skills by this author →
Website𝕏@rushyyyyyyyyyyyGitHub

security-scan

Scan Claude Code configurations for security vulnerabilities using AgentShield.

Updated Mar 19, 2026
Search Tags:#security#claude-code#secrets-detection#vulnerability-scan#agentshield#config-audit
One-click install
npx skills add https://github.com/RUSHYOP/imperium-cli --skill security-scan-rushyop
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: security-scan
Source: https://github.com/RUSHYOP/imperium-cli/tree/main/content/skills/security-scan
Command: npx skills add https://github.com/RUSHYOP/imperium-cli --skill security-scan-rushyop

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Audits Claude Code configurations to identify security vulnerabilities, misconfigurations, and injection risks using AgentShield across CLAUDE.md, settings.json, MCP configs, hooks, and agent definitions.

Core Features & Use Cases

  • Threat detection: scans CLAUDE.md for hardcoded secrets and prompt injection patterns.
  • Configuration hygiene: validates settings.json and MCP server entries to reduce risky permissions.
  • Holistic coverage: inspects hooks and agent definitions to prevent data leakage and insecure access.
  • Use Case: Before committing changes to a Claude Code project, run a scan to surface critical misconfigurations.

Quick Start

Run a security scan on the current project directory to generate a 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 configurations for security vulnerabilities and hardcoded secrets?▼

To scan Claude Code configurations for security vulnerabilities, run a scan on your local .claude folder to inspect CLAUDE.md, settings.json, MCP configs, hooks, and agent definitions for hardcoded secrets and misconfigurations.

What security risks should I check before committing Claude Code project files?▼

Before committing Claude Code project files, check for prompt injection patterns in CLAUDE.md, risky permissions in settings.json and MCP server entries, data leakage in hooks, and insecure access in agent definitions.

Do I need AgentShield installed to audit MCP configs and hooks?▼

Yes, you need AgentShield installed and accessible via npx or npm to audit MCP configs and hooks, as the security scan relies on AgentShield to identify vulnerabilities and misconfigurations across Claude Code files.

Can I detect prompt injection patterns in CLAUDE.md files?▼

Yes, you can detect prompt injection patterns in CLAUDE.md files by running a security scan that applies threat detection mechanisms to surface injection risks and hardcoded secrets within your Claude Code configurations.

How do I validate settings.json permissions to reduce risky configurations in Claude Code?▼

To validate settings.json permissions and reduce risky configurations in Claude Code, run a configuration hygiene scan that inspects settings.json and MCP server entries to surface critical misconfigurations before committing changes.

Related Skills

Explore More Software Engineering Skills→
KanakMalpaniKanakMalpani

security-scan

Audit Claude Code configurations for security vulnerabilities and misconfigurations using AgentShield.

Community
Intermediate
Zenobia000Zenobia000
2

security-scan

Audit Claude Code configuration files for security vulnerabilities and misconfigurations.

Community
Intermediate
kagentikagenti
292

cve

Scan project dependencies, source code, and documentation for known CVEs.

Official
Advanced
armanzeroeightarmanzeroeight
29

secrets-detector

Detect hardcoded secrets and API keys in source code repositories.

Community
Intermediate