npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@aiagentkit/agent-security-audit

v1.0.1

Published

AI-powered security audit tool that analyzes source code for vulnerabilities (OWASP Top 10)

Readme

agent-security-audit

Audita seguridad del código contra OWASP Top 10 usando IA.

Instalación

# Global
npm install -g @aiagentkit/agent-security-audit

# O sin instalar
npx @aiagentkit/agent-security-audit --path ./src

Uso

agent-security-audit --path ./src                           # auditar todo src/
agent-security-audit --path ./src/utils.ts                  # un solo archivo
agent-security-audit --path ./src --severity warning        # solo warning y critical
agent-security-audit --path ./src --extensions .ts,.prisma  # solo archivos .ts y .prisma
agent-security-audit --path ./src --format html             # salida HTML
agent-security-audit --path ./src --dry-run                 # preview sin escribir
agent-security-audit --path ./src --verbose                 # logs detallados

Proveedores

| Provider | Modelo Default | Auth | Notas | |----------|---------------|------|-------| | gemini | gemini-2.5-flash | GEMINI_API_KEY | Free tier disponible | | openai | gpt-4o | OPENAI_API_KEY | GPT-4o, GPT-4o-mini | | anthropic | claude-sonnet-4-20250514 | ANTHROPIC_API_KEY | Claude | | deepseek | deepseek-chat | DEEPSEEK_API_KEY | El más barato | | ollama | modelo instalado | Sin key | Local, gratis, privacidad |

Auto-detección: Si no especificas --provider, detecta automáticamente qué tienes configurado (keys en .env o Ollama corriendo).

Flags

| Flag | Descripción | Default | |------|-------------|---------| | --path | Archivo o carpeta a procesar | (requerido) | | --provider | gemini | openai | anthropic | deepseek | ollama | auto-detectado | | --model | Modelo a usar | según provider | | --base-url | URL del servidor (Ollama) | http://localhost:11434 | | --api-key | API key (opcional para Ollama) | .env | | --max-chars | Límite de chars por archivo | 15000 | | --output | Carpeta/archivo de salida | junto al archivo | | --extensions | Extensiones a procesar (CSV: .ts,.prisma) | todas | | --format | Formato de salida terminal | markdown | html | pdf | terminal | | --severity | Severidad mínima: info | warning | critical | info | | --dry-run | Solo preview, no escribir | false | | --verbose | Logs detallados | false |

Features

  • OWASP Top 10: SQL Injection, XSS, Secrets, Path Traversal, Auth, CSRF, SSRF, Crypto, Dependencies
  • Categorías de seguridad: cada finding indica la categoría OWASP
  • Filtro por severidad: --severity warning para ver solo issues importantes
  • Cache: hash MD5 para no regenerar archivos sin cambios
  • Auto-detección: detecta provider disponible al iniciar
  • Resiliencia: 3 reintentos con backoff ante errores de API
  • Truncado: archivos > --max-chars se recortan con aviso
  • Filtro por extensión: --extensions .ts,.prisma para limitar tipos de archivo

Requisitos

  • Node.js >= 18
  • Un proveedor de IA configurado (API key o Ollama local)

Licencia

MIT

Parte de AI Agent Toolkit.