cybersecurity-audit

Audit codebases for vulnerabilities across web, APIs, and LLM integrations.

15|2|Updated May 23, 2026
One-click install
npx skills add https://github.com/VKirill/antigravity-for-claude-code --skill cybersecurity-audit
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: cybersecurity-audit
Source: https://github.com/VKirill/antigravity-for-claude-code/tree/main/skills/cybersecurity-audit
Command: npx skills add https://github.com/VKirill/antigravity-for-claude-code --skill cybersecurity-audit

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires jq, curl, and includes references (resource) and scripts (resource) components.

What problem does it solve?

This Skill helps you quickly identify security weaknesses across a codebase—covering web, API, LLM-specific threats, secrets, crypto, supply-chain CVEs, and common exploit chains—then organizes findings into a prioritized remediation plan.

Core Features & Use Cases

  • OWASP Top 10 2025 (web): classifies issues by the most common real-world vulnerability families so findings map to actionable fixes.
  • OWASP API Top 10: audits REST/GraphQL authorization, auth failures, mass assignment, rate limiting gaps, and SSRF-type API risks.
  • OWASP LLM Top 10: checks prompt injection, sensitive disclosure, unsafe output handling, and excessive agent agency for AI-enabled apps.
  • Injection & auth/crypto deep dives: runs targeted detection guidance for SQL/NoSQL/command/template injection, Broken Access Control patterns, JWT/session pitfalls, and crypto/secrets mistakes.
  • Supply-chain via OSV.dev + native scanners: cross-checks dependency CVEs with OSV.dev and recommends ecosystem-native tooling.
  • Produces categorized findings + remediation plan: prioritizes fixes by exploitability and blast radius, and outputs defensive-only, non-exploit guidance.

Quick Start

Ask the auditor to run a defensive vulnerability sweep over your repository and return categorized findings with file paths and a prioritized remediation checklist.

Frequently Asked Questions about cybersecurity-audit

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run a security audit on my codebase to find vulnerabilities before release?

You can run a stack-agnostic security audit to identify vulnerabilities across web, APIs, LLM integrations, and supply chains. The audit cross-checks dependency CVEs with OSV.dev and outputs prioritized remediation plans with file and line context.

How does this check for OWASP LLM Top 10 vulnerabilities like prompt injection?

The LLM security audit evaluates prompt injection, sensitive data disclosure, unsafe output handling, and excessive agent agency. It classifies these issues according to the OWASP LLM Top 10 to map findings directly to actionable defensive fixes.

Can I use this to scan for SSRF and API authorization vulnerabilities in my REST and GraphQL endpoints?

Yes, the security audit checks REST and GraphQL APIs for authorization failures, mass assignment, rate limiting gaps, and SSRF risks. It categorizes these findings under the OWASP API Top 10 to guide your remediation efforts.

Do I need jq and curl installed to perform a supply chain vulnerability scan?

Yes, jq and curl are required dependencies for the skill. They are used to perform supply-chain checks and cross-reference dependency CVEs against the OSV.dev database during the security audit.

Will this security audit generate live exploit payloads to test my code?

No, the vulnerability hunting process is strictly defensive-only. It provides evidentiary findings and prioritized remediation planning without creating live exploit payloads for testing.

What is the best way to verify my project for security issues after a dependency bump?

Performing a post-dependency-bump verification security audit is the best approach. It cross-checks updated dependencies against OSV.dev for supply-chain CVEs and identifies any newly introduced vulnerabilities across your tech stack.