#447 · Primary category: AI Coding Assistants
VibeSec-Skill
This skill helps Claude write secure code and prevent common vulnerabilities.
Project last updated:02/17/26
GitHub Stars
1.2K
Forks
101
Contributors
3
License
Apache-2.0
Why we included this project
VibeSec-Skill is a set of instructions you install into Claude Code, Cursor, Codex, Copilot, or similar coding assistants so the model checks its own work for security problems as it writes. The author packed years of bug bounty experience into the skill, which steers the assistant away from common mistakes like hardcoded API keys, missing authentication, weak passwords, IDOR, XSS, SSRF, and SQL injection. It also includes framework and cloud specific guidance for React, Node, Python, Java, and the major cloud providers. This is not a scanner or a runtime tool; it works at the prompt level, changing how the coding model approaches security before code ships. If your team relies on AI-assisted development and wants a low-effort way to add a security mindset without standing up new infrastructure, this is worth a look.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.