🛡️
QualityPython

Web3 Audit

by shuvonsec

Web3 Audit is a Quality skill for Claude Code, published by shuvonsec in claude-bug-bounty.

4.2K stars767 forkson shuvonsec/claude-bug-bountyAdded 2026/08/16+1% in starsRepository updated 2026/08/10
ai-securitybug-bountybugcrowdclaude-aiclaude-codectiethical-hackinghackeronehackinghacking-toolpenetration-testingreconvulnerability-scanner
Install in seconds
Install Web3 Audit
Copy Web3 Audit into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/shuvonsec/claude-bug-bounty/tree/main/skills/web3-audit ~/.claude/skills/web3-audit

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/shuvonsec/claude-bug-bounty.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
skills/web3-audit/SKILL.md in shuvonsec/claude-bug-bounty
Installs to
~/.claude/skills/web3-audit
Collection
One of 16 skills cataloged from this repository
Category
Quality1354 skills

What Web3 Audit does

Web3 Audit catalogs 10 DeFi bug classes with grep patterns, Foundry PoC templates, and pre-dive kill signals for smart contract bug bounties.

Web3 Audit is cataloged under Quality on DirSkills. Web3 Audit comes from a repository tagged ai-security, bug-bounty, bugcrowd, claude-ai and claude-code.

Documentation

README

WEB3 SMART CONTRACT AUDIT

10 bug classes. Pre-dive kill signals. Foundry PoC template. Real paid examples.


PRE-DIVE KILL SIGNALS (check BEFORE any code review)

ZKsync lesson: $322M TVL + OZ audit + 750K LOC + 5 sessions = 0 findings. Large well-audited bridges are extremely hard.

  1. TVL < $500K → max payout capped too low for effort
  2. 2+ top-tier audits (Halborn, ToB, Cyfrin, OpenZeppelin) on simple protocol → bugs already found
  3. Protocol < 500 lines, single A→B→C flow → minimal attack surface
  4. Formula: max_realistic_payout = min(10% × TVL, program_cap) — if < $10K, skip

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Web3 Audit

  • What else does shuvonsec publish alongside Web3 Audit?

    Web3 Audit is one of 16 skills that DirSkills catalogs from shuvonsec/claude-bug-bounty, the repository it ships in. Its siblings there include Argus, Bug Bounty and Bug Bounty. Each one is a separate skill with its own page in this directory, installs the same way Web3 Audit does, and is maintained by shuvonsec in that same repository. The rest of the collection is listed on the shuvonsec/claude-bug-bounty page.

  • How does Web3 Audit compare to other Quality skills?

    Web3 Audit ranks #339 by stars among the 1354 Quality skills in this catalog. The most-starred ones next to it are Benchmark, Benchmark Optimization Loop and API Design Patterns. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Web3 Audit against them. Open each page to compare what they document and how they install.

More from shuvonsec/claude-bug-bounty

Web3 Audit is one of 16 skills cataloged on DirSkills from shuvonsec/claude-bug-bounty.

See all 16 skills
🔍
2w ago

Argus

Argus runs six automated scanners for web and LLM vulnerabilities: CORS misconfig, CRLF/host-header injection, NoSQL injection, JWT attacks, blind bug confirmation via OOB, and LLM red-teaming. Use it on JSON APIs, login endpoints, JWT auth, or any parameter that might reach the server.
Automation
4.2K767
🐞
2w ago

Bug Bounty

Bug Bounty guides a complete bug bounty workflow from reconnaissance and vulnerability hunting through validation and report writing, including LLM/AI security testing and A-to-B bug chaining. Use it for any bug bounty task, from starting a new target to writing the final submission.
Quality
4.2K767
🐞
2w ago

Bug Bounty

Bug Bounty provides a complete bug bounty workflow covering reconnaissance, vulnerability hunting, AI/LLM security testing, bug chaining, and report writing. Use it for starting new targets, hunting specific vuln classes, auditing source code, validating findings, or writing reports.
Quality
4.2K767
🎯
2w ago

Bug Bounty Methodology

Bug Bounty Methodology structures a hunting session around a five-phase workflow and a critical-thinking framework, so an agent can choose a goal, select techniques, and derive next actions. Use it at the start of a bug bounty session, when switching targets, or when unsure what to do next.
Quality
4.2K767
📝
2w ago

Bug Bounty Report Writing

Bug Bounty Report Writing provides templates, tone guidelines, CVSS scoring, and checklists for writing bug bounty reports for HackerOne, Bugcrowd, Intigriti, and Immunefi. Use it after validating a finding and before submitting.
Writing
4.2K767
🛡️
2w ago

CI/CD Security

CI/CD Security audits CI/CD pipelines for workflow injection, secret exfiltration, self-hosted runner poisoning, OIDC token theft, and supply chain attacks. Use it when a target has public repos or CI/CD infrastructure.
DevOps
4.2K767