jswortz/my-skills/audit-context-building

Claude Code and agent skill by jswortz/my-skills

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Use to build deep architectural context through granular code analysis before vulnerability hunting or security auditing.

Install

npx vskill@latest install jswortz/my-skills/audit-context-building

SKILL.md

The same SKILL.md was published earlier as jswortz/my-skills/audit-context-building.

Audit Context Building

Build deep architectural context through ultra-granular code analysis before vulnerability hunting.

Author: Omar Inuwa

When to Use

Use this skill when you need to:

  • Develop deep comprehension of a codebase before security auditing
  • Build bottom-up understanding instead of high-level guessing
  • Reduce hallucinations and context loss during complex analysis
  • Prepare for threat modeling or architecture review

What It Does

This skill governs how Gemini thinks during the context-building phase of an audit. When active, Gemini will:

  • Perform line-by-line / block-by-block code analysis
  • Apply First Principles, 5 Whys, and 5 Hows at micro scale
  • Build and maintain a stable, explicit mental model
  • Identify invariants, assumptions, flows, and reasoning hazards
  • Track cross-function and external call flows with full context propagation

Key Principle

This is a pure context building skill. It does NOT:

  • Identify vulnerabilities
  • Propose fixes
  • Generate proofs-of-concept
  • Assign severity or impact

It exists solely to build deep understanding before the vulnerability-hunting phase.

Installation

/plugin install trailofbits/skills/plugins/audit-context-building

Phases

  1. Initial Orientation - Map modules, entrypoints, actors, and storage
  2. Ultra-Granular Function Analysis - Line-by-line semantic analysis with cross-function flow tracking
  3. Global System Understanding - State/invariant reconstruction, workflow mapping, trust boundaries

Anti-Hallucination Rules

  • Never reshape evidence to fit earlier assumptions
  • Update the model explicitly when contradicted
  • Avoid vague guesses; use "Unclear; need to inspect X"
  • Cross-reference constantly to maintain global coherence

Related Skills

  • issue-writer - Write up findings after context is built
  • differential-review - Uses context-building for baseline analysis
  • spec-compliance - Compare understood behavior to documentation

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/jswortz/my-skills/audit-context-building/badge)](https://verified-skill.com/skills/jswortz/my-skills/audit-context-building)

Something wrong with this skill or its page? Tell us.