recon

Audit running web applications and generate a structured Confidence Letter.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/Bishwas-py/forge --skill recon-bishwas-py
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: recon
Source: https://github.com/Bishwas-py/forge/tree/main/skills/recon
Command: npx skills add https://github.com/Bishwas-py/forge --skill recon-bishwas-py

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires docker, psql, mysql, sqlite3, curl, openssl, git, lsof, python3, node, npx, gh, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Recon identifies and reports security, consistency, and quality issues in running web applications, delivering a structured Confidence Letter to guide fixes.

Core Features & Use Cases

  • Programmatic security scans (headers, CORS, cookies) and accessibility checks against live UI and API.
  • End-to-end UI/API/DB cross-checks that surface data mismatches and drift.
  • Confidence Letter generation for Forge to consume and triage tasks.

Quick Start

Run recon on a live web app to generate a Confidence Letter that Forge can parse and consume to drive fixes.

Frequently Asked Questions about recon

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate security auditing for a running web app?

Automate security auditing by running recon against a live web app to identify security, consistency, and quality issues. It uses Playwright for UI crawling and Bash scripts for deterministic checks across UI, API, and DB layers.

What is a Confidence Letter in web application security auditing?

A Confidence Letter is a structured report generated after auditing a web app, detailing identified security and consistency issues. It provides a triage format that downstream tools can parse to drive automated fixes.

Does this automated security audit require Docker to reproduce findings?

Yes, Docker is required to create per-branch environments that safely reproduce findings. Dependencies like psql, mysql, and sqlite3 are also needed to perform cross-checks between the UI, API, and database layers.

Can I check API and database consistency during a UI crawl?

Yes, you can perform end-to-end UI, API, and DB cross-checks simultaneously. The process uses Playwright for UI crawling and database clients to surface data mismatches and drift across the application stack.

What is the best way to scan live web app headers and CORS configurations?

The best way to scan live headers and CORS configurations is using automated programmatic security scans. This approach checks security headers, CORS policies, and cookies directly against the running UI and API endpoints.

When should I avoid running autonomous web app security scans?

You should avoid running autonomous security scans if the target web app lacks isolated Docker support or if the environment cannot safely accommodate per-branch reproduction of potential security findings and database modifications.