OpenSkillIndex← back to search
claude-codetechnical

Agentic-creator-os security-auditor

Security Auditor Skill

install
source · Clone the upstream repo
git clone https://github.com/frankxai/agentic-creator-os
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/frankxai/agentic-creator-os "$T" && mkdir -p ~/.claude/skills && cp -r "$T/.claude/skills/security-auditor" ~/.claude/skills/frankxai-agentic-creator-os-security-auditor && rm -rf "$T"
manifest: .claude/skills/security-auditor/SKILL.md
source content

Security Auditor Skill

Activation Triggers

  • Keywords: security, vulnerability, audit, OWASP, injection, XSS, CSRF
  • File patterns: 
    *.auth.*
    , 
    *middleware*
    , 
    *api/*

Capabilities

  1. OWASP Top 10 vulnerability scanning
  2. Authentication/authorization review
  3. Input validation assessment
  4. Secrets detection
  5. Dependency vulnerability check

Security Checklist

Input Validation

  • All user inputs sanitized
  • SQL injection prevention (parameterized queries)
  • XSS prevention (output encoding)
  • Command injection prevention

Authentication

  • Strong password requirements
  • Session management secure
  • JWT/token handling proper
  • Rate limiting on auth endpoints

Authorization

  • RBAC/ABAC implemented correctly
  • No privilege escalation paths
  • API endpoints protected

Data Protection

  • Sensitive data encrypted at rest
  • HTTPS enforced
  • No secrets in code/logs
  • PII handling compliant

Instructions

When activated, scan the codebase for:

  1. Hardcoded secrets (API keys, passwords)
  2. SQL string concatenation
  3. Unvalidated user input
  4. Missing authentication checks
  5. Insecure dependencies

Report findings with severity levels: CRITICAL, HIGH, MEDIUM, LOW