code-recon

Builds layered architectural context for security audits through phased codebase reconnaissance.

1|1|Updated May 21, 2026
One-click install
npx skills add https://github.com/naruto11eth/cryptoskills --skill code-recon-naruto11eth
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-recon
Source: https://github.com/naruto11eth/cryptoskills/tree/main/skills/code-recon
Command: npx skills add https://github.com/naruto11eth/cryptoskills --skill code-recon-naruto11eth

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Security auditors and code reviewers waste hours orienting themselves in unfamiliar codebases before they can find vulnerabilities. This Skill provides a structured, five-phase methodology to map architecture, trust boundaries, entry points, and security-critical functions before deep analysis begins. ## Core Features & Use Cases - Phased Recon Methodology: Progresses from overview and technology stack detection through architecture mapping, module deep dives, function-level analysis, and detail reconnaissance. - Trust Boundary & Entry Point Mapping: Produces concrete artifacts like endpoint inventories, data flow diagrams, and call graphs for security-critical functions. - Ready-Made Resources: Includes a recon checklist, a security question bank, a context document template, advanced techniques (CodeQL, AST analysis, smart contract storage inspection), and a full FastAPI walkthrough example. - Use Case: Before auditing a DeFi protocol or web API, run the recon phases to produce a Security Context Document identifying high-risk areas like race conditions in order creation or missing webhook idempotency checks. ## Quick Start Use the code-recon skill to build a security context document for this repository, mapping its architecture, trust boundaries, and highest-risk functions.

Frequently Asked Questions about code-recon

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

FAQPage Schema
How do I prepare a codebase for a security audit?

Start with a phased reconnaissance approach: identify the technology stack and dependencies, map the architecture and trust boundaries, enumerate all entry points, then analyze security-critical functions. Document findings in a structured context document before hunting for vulnerabilities.

How to map trust boundaries in a web application?

Identify where trust levels change: internet to API gateway, gateway to authenticated services, services to database, and services to third-party APIs. For each boundary, document the controls in place (TLS, JWT validation, parameterization) and the associated risks like injection or token forgery.

What tools help with codebase reconnaissance for security reviews?

Use grep patterns to enumerate routes and security-sensitive functions, tree-sitter for AST-based analysis, pyan3 or madge for call graphs, and CodeQL for taint tracking. Semgrep, trufflehog, and dependency auditors like npm audit complement manual review.

Does this recon methodology work for smart contracts?

Yes, it includes smart contract specific techniques such as bytecode decompilation with panoramix, storage slot analysis using cast, event log decoding, and questions covering reentrancy, oracle manipulation, and access control on privileged functions.

What should a security context document contain?

It should cover the technology stack, architecture diagram, trust boundaries, entry point inventory, authentication and authorization mechanisms, critical functions, data flows, existing security controls, high-risk areas, and open questions requiring further investigation.

When is static reconnaissance not enough for security analysis?

When code behavior depends on runtime state, use dynamic techniques like mitmproxy traffic capture, debug-mode logging, and database schema extraction. These reveal hidden endpoints, actual SQL queries, and authentication decisions that static reading misses.