VibeSec Skill — Development skill for Claude Code
to avoid getting hacked.
How to install VibeSec Skill
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open BehiSecc/VibeSec-Skill and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What VibeSec Skill does
to avoid getting hacked.
One of 2 entries listed from BehiSecc/VibeSec-Skill. The repository README
describes the whole collection, not this skill — read it on GitHub.
Alternatives in Development
- Getting Started With Spawner Skills — Getting Started with Spawner Skills skill 847 ★
- Getting Started With Claude Code — Your Guide to Installing and Using Claude Code for the Top 100 Recipes Last Updated: December 2025 238 ★
- Serve — Start a local http server on 127.0.0.1:4567 to avoid file:// CORS issues 102 ★
Repository README
This is the README for BehiSecc/VibeSec-Skill, shared by 2 entries
in this directory. It describes the repository, not this entry specifically.
VibeSec-Skill
**Stop vibe coding vulnerabilities into production.**
An AI skill that brings 5+ years of bug bounty hunting experience directly into your AI coding workflow - so LLM models write secure code from the start.
Introduction
Vibe coding is fun until your app ends up on social media for all the wrong reasons.
We have all seen the posts/memes:
- API keys hardcoded in JavaScript bundles
- IDOR vulnerabilities allowing user data dumps
- No authentication for sensitive pages
- Weak passwords for admin panels
Security gaps aren't obvious until someone exploits them. Without the right guidance, AI will confidently ship vulnerable patterns alongside your features.
VibeSec is an AI Skill that acts as a security-first co-pilot. It teaches your selected model to approach your code from a bug hunter's perspective, catching vulnerabilities before they ship.
📚 Table of Contents
[!Tip] This skill already covers 60-70% of the common vulnerabilities. However, if you need a more robust version with more vulnerability coverage, please visit [vibesec.sh](https://vibesec.sh/)
📥 Installation
Claude Code
Clone this repository: `git clone https://github.com/BehiSecc/VibeSec-Skill`
Add it to `~/.claude/skills` (global) or `.claude/skills` in your project directory (project-only).
Cursor
Clone this repository: `git clone https://github.com/BehiSecc/VibeSec-Skill`
Add it to `~/.cursor/skills` (global) or `.cursor/skills` in your project directory (project-only).
Codex
Clone this repository: `git clone https://github.com/BehiSecc/VibeSec-Skill`
Add it to `~/.agents/skills` (global) or `.agents/skills` in your project directory (project-only).
Github Copilot
...
Related Skills
Extract Voice
Extract creator Brand Voice Architecture — 10-section document with verbatim phrases_to_use + phrases_to_avoid
Context Budget
Analyze context window usage across agents, skills, MCP servers, and rules to find optimization opportunities.
Error
Log a bug or error atomically — creates entries in known-errors and errors-to-avoid, propagates the lesson via
Developer Anti Patterns To Avoid.Skill
ANTI-PATTERNS TO AVOID — extracted from roles.json deepPrompt for developer
Meridian Plugin Hermes Scrub
Meridian plugin: strip Hermes Agent's coding-harness fingerprint from the system prompt to avoid Extra-Usage m
Xhs Compliance Skill
Claude Code Agent Skill for XHS (小红书) content compliance — avoid banned words and traffic limits
Related Agents
Claude Code Tools
by Prasad Chalasani - Well-crafted toolset for session continuity, featuring skills/commands to avoid compacti
Aminet Researcher
Researches whether a tool or library already exists for AmigaOS before porting. Checks Aminet, Geek Gadgets, A
Autopilot Lite
Use when you want to run iterative autonomous development with PRD and progress tracking, fresh context per it
