VibeSec-Skill

VibeSec-Skill

Help Claude write secure code and prevent common vulnerabilities.

Agent SkillDevOpen source
Type
Agent Skill
Open source
Yes
GitHub Stars
★ 1.0k
Source
skill-github

Overview

VibeSec-Skill is an AI skill that brings years of vulnerability bounty hunting experience directly into the AI coding workflow, enabling LLM models to write secure code from the start. Acting as a security-first co-pilot, it teaches selected models to review code from a vulnerability hunter's perspective, catching flaws before code is released. Ideal for developers and teams looking to enhance code security.

Capabilities

  • Prevent IDOR and privilege escalation vulnerabilities
  • Prevent XSS, CSRF, and SSRF attacks
  • Prevent SQL injection and XXE attacks
  • Strengthen authentication and session management
  • Protect API security

Use cases

Automatically enforce access controls when building web applicationsAdd security headers to prevent client-side attacksValidate and sanitize all input dataFlag potential security issues

Setup

Requires: API Key
Clone the repository: `git clone https://github.com/BehiSecc/VibeSec-Skill`; add it to the corresponding skills directory (e.g., `~/.claude/skills` or `.claude/skills` within your project directory).

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

Which AI models does this skill support?

Supports Claude, Cursor, Codex, GitHub Copilot, and Antigravity.

How can I contribute code or report issues?

You can fork the repository and submit a pull request, or create an issue on GitHub.

Related skills