This is a systematic security audit skill that walks through your codebase looking for vulnerabilities and fixes them on the spot. It maps your attack surface by reading entry points, config files, and auth-related code, then identifies unguarded routes, external data entry points, and write operations. The methodical checklist approach (dependencies, secrets, XSS, auth, CORS, etc.) means it won't miss obvious categories, though with 338 installs and a warning from Gen Agent Trust Hub, you might want to review its changes carefully. Best used when you need a structured security pass before shipping or after adding new features that touch sensitive data.
npx -y skills add cognitedata/dune-skills --skill security --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
hoodini/ai-agents-skills
addyosmani/agent-skills
giuseppe-trisciuoglio/developer-kit
agamm/claude-code-owasp