Dev Loop Security Auditor

Use when the user asks for a security audit of a codebase, dependency vulnerability scan (npm audit, pip-audit, Trivy), secret scanning, Semgrep or CodeQL findings, or OWASP Top 10 review. Produces prioritized findings with fixes. Not for SAST/DAST pipeline design (use security-sast-dast) or pentest engagements (use pentesting).

45 stars 6 forksSecurity

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add j4flmao/agent-skills --skill dev-loop-security-auditor
Manual install
git clone --depth 1 https://github.com/j4flmao/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/dev-loop/security-auditor ~/.claude/skills/dev-loop-security-auditor

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Security Auditor

## Purpose
Systematically identify, assess, and remediate security vulnerabilities in applications — including dependency vulnerabilities, code-level flaws, misconfigurations, and authentication/authorization weaknesses — using automated scanning tools and manual review techniques.

## Agent Protocol

### Trigger
Exact user phrases: "security audit", "vulnerability scan", "security review", "dependency check", "SAST", "DAST", "penetration test", "CVE", "OWASP", "security assessment", "threat modeling".

### Input Context
- Application type (web app, API, mobile, desktop, CLI, library)
- Language and framework (affects vulnerability patterns)
- Deployment environment (cloud, on-prem, hybrid, air-gapped)
- Regulatory requirements (SOC2, HIPAA, PCI-DSS, GDPR, FedRAMP)
- Authentication method (OAuth2, SAML, API keys, JWT, session cookies)
- Data sensitivity (PII, financial, health, credentials, tokens)
- Existing security measures (WAF, IDS, rate limiting, encryption)
- Recent security incidents or CVEs

### Output Artifact
Security audit report with identified vulnerabilities by severity, remediation steps, and priority.

### Response Format
```
Scope: {repo/service, commit}
Findings: [{severity}] {title} — {file:line} — {CWE/OWASP ref}
  Impact: {what an attacker gains}
  Fix: {concrete change}
Tools run: {SAST/SCA/secrets scan + versions}
Not covered: {areas out of scope}
```

### Completion Criteria
- [ ] Dependency vulnerability scan completed
Read the full skill on GitHub

Details

Skill name
dev-loop-security-auditor
Path
skills/dev-loop/security-auditor/SKILL.md
License
MIT
Repo updated
17 November 2026

FAQ

What does the Dev Loop Security Auditor skill do?

Use when the user asks for a security audit of a codebase, dependency vulnerability scan (npm audit, pip-audit, Trivy), secret scanning, Semgrep or CodeQL findings, or OWASP Top 10 review. Produces prioritized findings with fixes. Not for SAST/DAST pipeline design (use security-sast-dast) or pentest engagements (use pentesting).

How do I install the Dev Loop Security Auditor skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add j4flmao/agent-skills --skill dev-loop-security-auditor. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Dev Loop Security Auditor popular?

It lives in j4flmao/agent-skills, which has 45 GitHub stars and 6 forks.

Related skills

Agent Observability

45

j4flmao/agent-skills

Use when the user asks about agent observability, tracing agent reasoning, debugging an agent loop, OpenTelemetry GenAI spans for LLM calls, LLM cost tracking per agent, agent audit logs or hallucination/eval monitoring in production. Produces instrumentation config, trace schema, dashboards, alerts and cost attribution. Not for generic service tracing without LLMs (use devops-opentelemetry).

DevOps & Cloud

AI Agent Architectures

45

j4flmao/agent-skills

Use when the user asks to build an AI agent, design an agent that calls tools and keeps memory, write an agent system prompt or pick an agent framework (Claude Agent SDK, OpenAI Agents SDK, LangGraph). Produces an architecture brief covering loop, tools, memory, guardrails and evals, routing depth to child skills. Not for workflow patterns (use ai-agentic-workflows).

AI, LLMs & Agents

AI Agent Core Loop

45

j4flmao/agent-skills

Use when the user asks about the agent loop, ReAct vs plan-and-solve, re-planning, Reflexion, an agent stuck in a loop, max iterations or termination conditions. Produces a loop spec or patch with state, success predicate, caps and no-progress detection. Not for overall agent design (use ai-agent-architectures) or tool schemas (use tool-calling-principles).

AI, LLMs & Agents

Enterprise Compliance Audit

45

j4flmao/agent-skills

Use when the user asks to prepare evidence for a SOC 2 audit, ISO 27001 certification, GDPR, HIPAA or PCI DSS compliance, control mapping, auditor requests or continuous compliance monitoring. Produces a control matrix, evidence plan and audit-readiness checklist. Not for vulnerability scanning (use dev-loop-security-auditor) or pentests (use pentesting).

Security

Desktop Electron

45

j4flmao/agent-skills

Use when the user asks about Electron, main and renderer process IPC security, contextBridge and preload scripts, contextIsolation and sandbox, Electron Forge or electron-builder packaging, code signing or auto-update. Produces a secure Electron app structure and release setup. Not for Tauri apps (use desktop-tauri).

Security

Frontend Security

45

j4flmao/agent-skills

Use when the user asks how to prevent XSS and set a content security policy, CSP nonces, Trusted Types, DOMPurify, CSRF tokens, SRI, secure cookies, clickjacking or security headers for a web app. Produces frontend hardening code and header config. Not for server-side OWASP testing (use owasp-web-security) or login flows (use frontend-authentication).

Security

Browse the most popular Claude skills, all security skills, or write your own with the skills generator.