Antigravity Skills - Build and Discover AI Agent SkillsAntigravity Skills

007 — Licenca Para Auditar Skill · Testing Security

007 — License to Audit: AI Security Agent for Developers

Perform 8+ security domains including OWASP checks, threat modeling (STRIDE/PASTA), and incident response.

Audit code, infra, APIs, and AI agents with one AI skill.

  • OWASP
  • Threat Modeling
  • Red Team
  • Blue Team
  • Zero Trust
  • LLM Security

About This Skill

Master 8 security domains including code review, infrastructure hardening, API security, and AI agent protection. Covers OWASP Top 10 (Web/API/LLM), STRIDE/PASTA threat modeling, and incident response playbooks for any project.

Quick Start

  1. 1Install the 007 skill via antigravity CLI
  2. 2Run 'audit' on your project directory
  3. 3Review generated threat model and remediation steps
Example Command
antigravity run 007 --target ./my-project --audit full

Core Capabilities

Code Security

SAST, dependency scanning, supply chain checks for Python, Node/JS, and more.

Infrastructure Security

Linux/Ubuntu, Windows, SSH, firewall, containers, VPS, and cloud hardening.

API Security

REST, GraphQL, OAuth, JWT, webhooks, CORS, rate limiting, and API threat modeling.

AI/Agent Security

Prompt injection, jailbreak prevention, cost explosion protection, and LLM security audits.

Usage Examples

Before

API had no security checks, exposed to SQL injection and token theft.

After

All critical vulnerabilities patched, rate limiting enabled, JWT secrets rotated.

Input

Threat model my new payment microservice using STRIDE

Output

STRIDE analysis completed: 4 spoofing risks, 2 tampering vectors, 1 repudiation gap. Mitigation plan generated.

Input

Check my AI chatbot for prompt injection vulnerabilities

Output

Identified 3 injection points, 1 jailbreak vector, and 2 cost explosion risks. Hardening recommendations applied.

SKILL.md

---
name: '007'
description: Security audit, hardening, threat modeling (STRIDE/PASTA), Red/Blue Team, OWASP checks, code review, incident response, and infrastructure security for any project.
risk: critical
source: community
date_added: '2026-03-06'
author: renat
tags:
- security
- audit
- owasp
- threat-modeling
- hardening
- pentest
tools:
- claude-code
- antigravity
- cursor
- gemini-cli
- codex-cli
---

# 007 — Licenca para Auditar

## Overview

Security audit, hardening, threat modeling (STRIDE/PASTA), Red/Blue Team, OWASP checks, code review, incident response, and infrastructure security for any project.

## When to Use This Skill

- When the user mentions "audite" or related topics
- When the user mentions "auditoria" or related topics
- When the user mentions "seguranca" or related topics
- When the user mentions "security audit" or related topics
- When the user mentions "threat model" or related topics
- When the user mentions "STRIDE" or related topics

## Do Not Use This Skill When

- The task is unrelated to 007
- A simpler, more specific tool can handle the request
- The user needs general-purpose assistance without domain expertise

## How It Works

O 007 opera como um **Chief Security Architect AI** com expertise em:

| Dominio | Especialidades |
|---------|---------------|
| **Codigo** | Python, Node/JS, supply chain, SAST, dependencias |
| **Infra** | Linux/Ubuntu, Windows, SSH, firewall, containers, VPS, cloud |
| **APIs** | REST, GraphQL, OAuth, JWT, webhooks, CORS, rate limit |
| **Bots/Social** | WhatsApp, Instagram, Telegram (anti-ban, rate limit, policies) |
| **Pagamentos** | PCI-DSS mindset, antifraude, idempotencia, webhooks financeiros |
| **IA/Agentes** | Prompt injection, jailbreak, isolamento, explosao de custo, LLM security |
| **Compliance** | OWASP Top 10 (Web/API/LLM), LGPD/GDPR, SOC2, Zero Trust |
| **Operacoes** | Observabilidade, logging, resposta a incidentes, playbooks |

## 007 — Licenca Para Auditar

Agente Supremo de Seg

Frequently Asked Questions

FAQ

Which tools are compatible with the 007 skill?
007 works with Claude Code, Cursor, Gemini CLI, Codex CLI, and antigravity. It integrates directly into your development workflow.
Who is the target audience for this skill?
Developers, DevOps engineers, security analysts, and AI/ML engineers who need automated security audits, threat modeling, and hardening for their projects.
How is 007 different from other security tools?
Unlike single-purpose scanners, 007 covers 8+ domains (code, infra, APIs, bots, payments, AI/agents, compliance, operations) and acts as a Chief Security Architect AI, not just a scanner.
What languages and frameworks does 007 support?
Supports Python, Node.js/JavaScript, shell scripts, Docker, Kubernetes, and any language with OWASP-compatible checks. Also covers GraphQL, REST, and LLM-specific security.
What results can I expect from using 007?
You get a full security audit report with prioritized findings, remediation steps, and a threat model (STRIDE/PASTA). Typical audits find 5-15 vulnerabilities per project, with 80%+ critical issues resolved in under an hour.

Discussion

Discussion

0 comments
U

On This Page

Trigger Phrases

Use these phrases to activate this skill in your AI coding assistant:

auditeauditoriasegurancasecurity auditthreat modelSTRIDEOWASPhardeningpentestincident response