3stoneBrother3stoneBrotherCommunityยท2 Agent Skills Included

code-audit

Deep AI security audits that find real code vulnerabilities

Audits source code across 9 languages and 14 frameworks to find SQL injection, RCE, SSRF, and 55+ other vulnerability types. Eliminates false positives by forcing the agent to verify every finding against actual files and real code lines. Runs quick, standard, or deep multi-agent scans and chains small flaws into full attack paths with clear reports.
npx skills add 3stoneBrother/code-audit --all -g -y
Available:

Instructs the AI agent on how to run security audits step by step, including anti-hallucination rules, attack-chain reasoning, scan modes, and which reference modules to load per tech stack.

All Skills in This Repository (2)

Pure Emerald Level Indicators

Frequently Asked Questions

FAQPage Schema
How to install code-audit?โ–ผ

Run `npx skills add 3stoneBrother/code-audit --all -g -y` in your terminal to install the skill globally for your AI agent.

What vulnerabilities can code-audit find?โ–ผ

It detects 55+ vulnerability types including SQL injection, RCE, deserialization, SSRF, XSS, and business logic flaws across 9 programming languages.

How do I run a security audit with AI?โ–ผ

Just ask your agent to 'audit this project' or use /code-audit, then pick quick, standard, or deep mode depending on how thorough you need the scan to be.

Does code-audit work with Claude Code?โ–ผ

Yes. It is built for Claude Code and follows the standard SKILL.md format, so it also works with compatible agents like Cursor and Codex.

How does code-audit avoid false positives?โ–ผ

It enforces strict anti-hallucination rules: every reported issue must be verified against real files and actual code read by the agent, never guessed from typical project structures.

Related Repositories in Software Engineering

View All in Software Engineeringโ†’