# BehiSecc/VibeSec-Skill

This skill helps Claude write secure code and prevent common vulnerabilities.

Repository: https://github.com/BehiSecc/VibeSec-Skill
Canonical: https://ross.abutalabs.com/products/vibesec-skill
License: Apache-2.0
License Family: permissive
Last push: 2026-02-17T14:03:16+00:00

## Health v2 (maintenance only)
Score: 46/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 68, release rhythm 35, longevity 15
- inputs: {"age_days": 212, "days_push": 197, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1220, forks 101 (observed 2026-08-28T04:04:01.876499+00:00)

## What it is
VibeSec-Skill is an AI skill (prompt/instruction pack) that teaches LLM coding assistants like Claude Code, Cursor, Codex, Copilot, and Antigravity to write secure code and avoid common vulnerabilities. It packages bug-bounty-derived security guidance covering access control, client-side, and server-side vulnerability classes.

## Use cases
- prevent AI from writing insecure code
- stop hardcoded API keys in generated code
- avoid IDOR vulnerabilities in AI-built apps
- add security guidance to Claude Code
- make Cursor write code with authentication and access control
- catch XSS and SQL injection patterns in AI-generated code
- secure vibe-coded projects before shipping

## When to choose
- you use AI coding assistants and want security-first output
- you are vibe coding an app and worried about common vulnerabilities
- you want lightweight security rules installed as a skill in Claude Code, Cursor, Codex, Copilot, or Antigravity

## When to avoid
- you need a real static analysis or SAST scanner with actual code scanning
- you need exhaustive vulnerability coverage beyond the free subset (the paid vibesec.sh version claims more)
- your project does not use LLM-based coding tools

## Facets
- artifact type: plugin
- maturity: active
- function: security, developer-tools, code-review, vulnerability-scanning
- domain: security, developer-tools, artificial-intelligence
- platform: cross-platform
- tags: ai-skill, claude, secure-coding, bug-bounty, vibe-coding, llm-workflow, owasp

## Member repositories
- BehiSecc/VibeSec-Skill (main) score 46

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:01.876499+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:15:54.860592+00:00, confidence not recorded.
  - readme: https://github.com/BehiSecc/VibeSec-Skill (fetched 2026-08-28T04:04:01.876499+00:00, sha e233aacf7697)
- Data as of 2026-08-30T08:39:29.467469+00:00.