Back to list
TaylorHuston

security-audit

by TaylorHuston

A customizable life management framework for Claude Code - skills, agents, and workflows for personal productivity

12🍴 2📅 Jan 24, 2026

SKILL.md


name: security-audit description: "Comprehensive security audit of codebase using multiple security-auditor agents. Use before production deployments or after major features." model: claude-sonnet-4-20250514 allowed-tools: Read, Write, Glob, Grep, Task

/security-audit

Multi-agent security audit with findings saved to timestamped report.

Usage

/security-audit yourbench           # Full security review
/security-audit coordinatr          # Audit specific project

Audit Dimensions

Five security-auditor agents run in parallel:

AgentFocus AreaChecks
Agent 1: Auth & AccessAuthentication, AuthorizationJWT handling, session management, RBAC, privilege escalation
Agent 2: Input & DataInjection, ValidationSQL injection, XSS, command injection, input sanitization
Agent 3: Crypto & SecretsCryptography, SecretsHardcoded credentials, weak crypto, key management, PII
Agent 4: Config & DeployConfiguration, InfrastructureCORS, CSRF, security headers, exposed endpoints, debug mode
Agent 5: DependenciesSupply Chain, LibrariesVulnerable packages, outdated deps, license issues

OWASP Top 10 Coverage

OWASP RiskCoverage
A01 Broken Access ControlAgent 1
A02 Cryptographic FailuresAgent 3
A03 InjectionAgent 2
A04 Insecure DesignAgents 1, 4
A05 Security MisconfigurationAgent 4
A06 Vulnerable ComponentsAgent 5
A07 Auth FailuresAgent 1
A08 Data Integrity FailuresAgents 2, 3
A09 Logging FailuresAgent 4
A10 SSRFAgent 2

Execution Flow

1. Validate Project

ls spaces/[project]/

2. Launch Parallel Audits

5 security-auditor agents run concurrently with focused prompts.

3. Consolidate Findings

Aggregate by:

  • Severity: Critical, High, Medium, Low, Info
  • Category: OWASP classification
  • Location: File path + line number
  • Remediation: Specific fix guidance

4. Generate Report

Write: .claude/temp/security-audit-[project]-[timestamp].md

Report Structure

# Security Audit: [Project Name]
**Date**: YYYY-MM-DD HH:MM:SS

## Executive Summary
- Critical issues: X
- High severity: Y
- Total findings: Z

## Critical Issues
### [Issue Title]
- **Severity**: Critical
- **Category**: SQL Injection (CWE-89)
- **Location**: src/api/users.py:42
- **Description**: [What's wrong]
- **Impact**: [What could happen]
- **Remediation**: [How to fix]

## High Severity Issues
[...]

## Recommendations
- Priority actions
- Long-term improvements

## Scan Coverage
- Files scanned: X
- Technologies: Z

When to Use

  • Before production deployments
  • After major feature additions
  • Monthly security reviews
  • Before external security audits
  • After dependency updates

Output Location

.claude/temp/security-audit-yourbench-2026-01-08-143022.md

Reports saved to .claude/temp/ (gitignored) for review.

Notes

  • Read-only: No code changes made
  • Non-blocking: Doesn't prevent commits
  • Parallel execution: Agents run concurrently
  • False positives possible: Manual review recommended

Integration

Implement security feature → /security-audit → Fix issues → /commit

Score

Total Score

60/100

Based on repository quality metrics

SKILL.md

SKILL.mdファイルが含まれている

+20
LICENSE

ライセンスが設定されている

0/10
説明文

100文字以上の説明がある

+10
人気

GitHub Stars 100以上

0/15
最近の活動

3ヶ月以内に更新がある

0/10
フォーク

10回以上フォークされている

0/5
Issue管理

オープンIssueが50未満

+5
言語

プログラミング言語が設定されている

+5
タグ

1つ以上のタグが設定されている

0/5

Reviews

💬

Reviews coming soon