Skip to content
Back to search

web3-bug-bounty-hunting-ai-skills

18 Claude Code skill files for smart contract security — built from 2,749 Immunefi reports, 681 DeFiHack reproductions, and real hunt experience

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/awarexone--web3-bug-bounty-hunting-ai-skills/badge.svg)](/listings/awarexone--web3-bug-bounty-hunting-ai-skills)

HTML

<a href="/listings/awarexone--web3-bug-bounty-hunting-ai-skills"><img src="/api/listings/awarexone--web3-bug-bounty-hunting-ai-skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

**Option 1 - drop into your existing project:**

git clone https://github.com/Awarexone/web3-bug-bounty-hunting-ai-skills.git .claude/skills/web3
claude

Then in Claude Code:

Read all files in .claude/skills/web3/ starting from 00-START-HERE.md

**Option 2 - standalone workspace:**

git clone https://github.com/Awarexone/web3-bug-bounty-hunting-ai-skills.git
cd web3-bug-bounty-hunting-ai-skills
claude

**Option 3 - just the essentials:**

Read 02-bug-classes.md and 04-poc-and-foundry.md

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 119 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <div align="center">
  2. # web3-bug-bounty-hunting-ai-skills
  3. Smart contract bug bounty skills for Claude Code, Claude AI, and other AI tools.
  4. Built from 2,749 Immunefi reports, 681 DeFiHack reproductions, and real hunts.
  5. [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](./LICENSE)
  6. [![Skills](https://img.shields.io/badge/skills-11-blue)]()
  7. [![Immunefi](https://img.shields.io/badge/Immunefi%20reports-2%2C749-orange)]()
  8. [![DeFiHackLabs](https://img.shields.io/badge/DeFiHack%20reproductions-681-red)]()
  9. Built and maintained by **AwareXone** - [Website](https://awarexone.com) · [X](https://x.com/awarexone) · [GitHub](https://github.com/Awarexone)
  10. </div>
  11. ---
  12. Most hunters still do everything manually. Read contracts in a browser, grep from memory, rewrite Foundry templates each hunt, draft reports from scratch.
  13. These skill files load into Claude Code (or any AI) and give it a complete smart contract security knowledge base - target scoring, bug patterns, grep arsenal, PoC templates, report format, and real case studies. One `claude` command, then start hunting.
  14. Works with: **Claude Code**, **Claude.ai**, **Cursor**, **any AI that reads files**.
  15. ---
  16. ## Files
  17. | File | Contents |
  18. |------|----------|
  19. | [`00-start-here.md`](./00-START-HERE.md) | Index + how to navigate |
  20. | [`01-foundation.md`](./01-foundation.md) | Hunter mindset, target scoring (10-point scorecard), recon setup |
  21. | [`02-bug-classes.md`](./02-bug-classes.md) | All 10 bug classes - patterns, Solidity examples, real Immunefi findings |
  22. | [`03-grep-arsenal.md`](./03-grep-arsenal.md) | Grep/regex patterns for every bug class |
  23. | [`04-poc-and-foundry.md`](./04-poc-and-foundry.md) | 18 Foundry PoC templates - fill in address, run `forge test` |
  24. | [`05-triage-report-examples.md`](./05-triage-report-examples.md) | 7-question validation gate, Immunefi report format, 20 paid examples |
  25. | [`06-methodology-research.md`](./06-methodology-research.md) | Trail of Bits, SlowMist, ConsenSys, Cyfrin, Nethermind methodology |
  26. | [`07-case-study-role-misconfiguration.md`](./07-case-study-role-misconfiguration.md) | Full hunt walkthrough - role misconfiguration bug, real findings |
  27. | [`08-ai-tools.md`](./08-ai-tools.md) | Shannon, SmartGuard, CAI Framework, LuaN1ao agent setup |
  28. | [`09-case-study-hardened-l2-bridge.md`](./09-live-hunt-zksync.md) | Defense study - 25 attack vectors tested on a hardened L2 bridge |
  29. | [`36-solidity-audit-mcp.md`](./36-solidity-audit-mcp.md) | MCP server - run Slither + Aderyn + SWC inside Claude Code |
  30. Read in order. Each file ends with `→ NEXT`. After file 05 you can hunt on your own.
  31. ---
  32. ## The 10 Bug Classes
  33. ```
  34. 01 Accounting Desync → most common Critical (37% of all payouts)
  35. 02 Access Control → most common High
  36. 03 Incomplete Path → missing modifier on a sibling function
  37. 04 Off-by-One → boundary operators, index errors
  38. 05 Oracle Price → TWAP manipulation, stale prices
  39. 06 ERC4626 Vaults → share inflation, rounding attacks
  40. 07 Reentrancy → cross-function, cross-contract, read-only
  41. 08 Flash Loan → price manipulation, economic attacks
  42. 09 Signature Replay → cross-chain replay, missing nonce/chainId
  43. 10 Proxy/Upgrade → uninitialized implementation, storage collision
  44. ```
  45. > Read ALL sibling functions. If `vote()` has a modifier, check `poke()`, `reset()`, `harvest()`.
  46. > The missing modifier on the sibling is the bug. This one rule explains 19% of all Criticals.
  47. ---
  48. ## Setup
  49. **Option 1 - drop into your existing project:**
  50. ```bash
  51. git clone https://github.com/Awarexone/web3-bug-bounty-hunting-ai-skills.git .claude/skills/web3
  52. claude
  53. ```
  54. Then in Claude Code:
  55. ```
  56. Read all files in .claude/skills/web3/ starting from 00-START-HERE.md
  57. ```
  58. **Option 2 - standalone workspace:**
  59. ```bash
  60. git clone https://github.com/Awarexone/web3-bug-bounty-hunting-ai-skills.git
  61. cd web3-bug-bounty-hunting-ai-skills
  62. claude
  63. ```
  64. **Option 3 - just the essentials:**
  65. ```
  66. Read 02-bug-classes.md and 04-poc-and-foundry.md
  67. ```
  68. ---
  69. ## Numbers
  70. | | |
  71. |---|---|
  72. | Immunefi reports analyzed | 2,749 |
  73. | Critical findings | 406 |
  74. | High findings | 616 |
  75. | Total paid by Immunefi | $100M+ |
  76. | DeFiHackLabs reproductions | 681 |
  77. | Nethermind audit reports | 166 |
  78. | Protocols covered | 51 |
  79. ---
  80. ## Related
  81. | Repo | What it does |
  82. |------|-------------|
  83. | [Agentic-Bug-Hunter](https://github.com/Awarexone/Agentic-Bug-Hunter) | Point at a target → full attack surface map + Immunefi/Bugcrowd report |
  84. | [public-skills-builder](https://github.com/Awarexone/public-skills-builder) | Feed 500 public writeups → get skill files like these back out |
  85. ---
  86. MIT License. Use it, fork it, build on it.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.