everything-claude-code/skills/security-scan/SKILL.md

name, description, origin

name	description	origin
security-scan	Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.	ECC

Security Scan Skill

Audit your Claude Code configuration for security issues using AgentShield.

When to Activate

• Setting up a new Claude Code project
• After modifying .claude/settings.json, CLAUDE.md, or MCP configs
• Before committing configuration changes
• When onboarding to a new repository with existing Claude Code configs
• Periodic security hygiene checks

What It Scans

File	Checks
CLAUDE.md	Hardcoded secrets, auto-run instructions, prompt injection patterns
settings.json	Overly permissive allow lists, missing deny lists, dangerous bypass flags
mcp.json	Risky MCP servers, hardcoded env secrets, npx supply chain risks
hooks/	Command injection via interpolation, data exfiltration, silent error suppression
agents/*.md	Unrestricted tool access, prompt injection surface, missing model specs

Prerequisites

AgentShield must be installed. Check and install if needed:

# Check if installed
npx ecc-agentshield --version

# Install globally (recommended)
npm install -g ecc-agentshield

# Or run directly via npx (no install needed)
npx ecc-agentshield scan .

Usage

Basic Scan

Run against the current project's .claude/ directory:

# Scan current project
npx ecc-agentshield scan

# Scan a specific path
npx ecc-agentshield scan --path /path/to/.claude

# Scan with minimum severity filter
npx ecc-agentshield scan --min-severity medium

Output Formats

# Terminal output (default) — colored report with grade
npx ecc-agentshield scan

# JSON — for CI/CD integration
npx ecc-agentshield scan --format json

# Markdown — for documentation
npx ecc-agentshield scan --format markdown

# HTML — self-contained dark-theme report
npx ecc-agentshield scan --format html > security-report.html

Auto-Fix

Apply safe fixes automatically (only fixes marked as auto-fixable):

npx ecc-agentshield scan --fix

This will:

• Replace hardcoded secrets with environment variable references
• Tighten wildcard permissions to scoped alternatives
• Never modify manual-only suggestions

Opus 4.6 Deep Analysis

Run the adversarial three-agent pipeline for deeper analysis:

# Requires ANTHROPIC_API_KEY
export ANTHROPIC_API_KEY=your-key
npx ecc-agentshield scan --opus --stream

This runs:

1. Attacker (Red Team) — finds attack vectors
2. Defender (Blue Team) — recommends hardening
3. Auditor (Final Verdict) — synthesizes both perspectives

Initialize Secure Config

Scaffold a new secure .claude/ configuration from scratch:

npx ecc-agentshield init

Creates:

• settings.json with scoped permissions and deny list
• CLAUDE.md with security best practices
• mcp.json placeholder

GitHub Action

Add to your CI pipeline:

- uses: affaan-m/agentshield@v1
  with:
    path: '.'
    min-severity: 'medium'
    fail-on-findings: true

Severity Levels

Grade	Score	Meaning
A	90-100	Secure configuration
B	75-89	Minor issues
C	60-74	Needs attention
D	40-59	Significant risks
F	0-39	Critical vulnerabilities

Interpreting Results

Critical Findings (fix immediately)

• Hardcoded API keys or tokens in config files
• Bash(*) in the allow list (unrestricted shell access)
• Command injection in hooks via ${file} interpolation
• Shell-running MCP servers

High Findings (fix before production)

• Auto-run instructions in CLAUDE.md (prompt injection vector)
• Missing deny lists in permissions
• Agents with unnecessary Bash access

Medium Findings (recommended)

• Silent error suppression in hooks (2>/dev/null, || true)
• Missing PreToolUse security hooks
• npx -y auto-install in MCP server configs

Info Findings (awareness)

• Missing descriptions on MCP servers
• Prohibitive instructions correctly flagged as good practice

Infrastructure Security Operations

Beyond Claude Code config scanning, this skill covers broader infrastructure security hygiene.

Repository Security Checks

# Check Dependabot alerts across repos
gh api repos/{owner}/{repo}/dependabot/alerts --jq '.[].security_advisory.summary'

# Check for exposed secrets in recent commits
gh api repos/{owner}/{repo}/secret-scanning/alerts --jq '.[].state'

# Check code scanning alerts (CodeQL)
gh api repos/{owner}/{repo}/code-scanning/alerts --jq '.[].rule.description'

API Key Hygiene

Track and rotate API keys on a schedule:

Category	Rotation Frequency
LLM APIs (OpenAI, Anthropic, etc.)	Quarterly
Search APIs (Exa, Brave, Firecrawl)	Quarterly
Social APIs (X, LinkedIn)	On compromise only
Infrastructure (Supabase, GitHub tokens)	Quarterly
Payment (Stripe)	On compromise only
OAuth tokens (Oura, Google)	Auto-refresh

Quick Security Audit

1. Check all repos for Dependabot alerts
2. Check for exposed secrets in recent commits
3. Verify critical services are responding
4. Check SSL cert expiry for deployed domains
5. Review API key scopes (are any over-permissioned?)

Deep Security Audit

1. Full dependency tree analysis for each repo
2. API key scope review
3. Review LaunchAgent/cron configurations for security implications
4. Check for hardcoded secrets in codebase (beyond .env)
5. Network exposure audit (what ports are open?)
6. Review OAuth token scopes and expiry
7. License compliance check

Incident Response

If a key is compromised:

1. Immediately rotate the affected key
2. Check service logs for unauthorized usage
3. Review git history for when/how it was exposed
4. Update .env files across all systems
5. Assess impact and notify stakeholders

Links

• GitHub: github.com/affaan-m/agentshield
• npm: npmjs.com/package/ecc-agentshield