web3-audit

A smart-contract security audit command that checks code for ten listed bug types, such as access-control errors, reentrancy, and oracle mistakes. It can also create a Foundry proof-of-concept template for confirmed issues.

In plain words
What is it for?
Use it to review a Solidity contract from a file, GitHub repository, or pasted code, then investigate suspected vulnerabilities and prepare a proof-of-concept template.
Why use it?
It gives a structured way to look for common contract flaws and filters out targets that may not justify the effort. This helps avoid writing reports about unconfirmed or low-value findings.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/zyrexnn/cybermes/web3-audit
Clone the repo
git clone --depth 1 https://github.com/Zyrexnn/Cybermes
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,834 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 98% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01834
Opus 5 $0.00000 $0.00917
Sonnet 5 $0.00000 $0.00367
Haiku 4.5 $0.00000 $0.00183

Measured yesterday against content hash c6202c7230a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

web3-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

98% identical to web3-audit — 1 line differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

knowledge/Claude-BugHunter/commands/web3-audit.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: web3-audit description: Smart contract security audit — runs through 10 bug class checklist (accounting desync, access control, incomplete path, off-by-one, oracle errors, ERC4626, reentrancy, flash loan, signature replay, proxy/upgrade). Applies pre-dive kill signals first. Generates Foundry PoC template for confirmed findings. Usage: /web3-audit <contract.sol>

/web3-audit

Smart contract security audit using the 10-bug-class methodology.

Usage

/web3-audit VulnerableContract.sol
/web3-audit https://github.com/protocol/contracts
/web3-audit [paste contract code]

Step 0: Pre-Dive Kill Signals

ALWAYS check these BEFORE reading any code:

1. TVL < $500K → max payout too low for effort → SKIP
2. 2+ top-tier audits (Halborn, ToB, Cyfrin, OZ) on simple protocol → SKIP
3. Protocol < 500 lines, single A→B→C flow → minimal attack surface → SKIP
4. max_payout = min(10% × TVL, program_cap) → if < $10K → SKIP

Formula: Is [TVL * 10%] > [hours I'll spend * hourly rate]? If not, skip.

Only proceed if score >= 6/10:

  • TVL > $10M: +2
  • Immunefi Critical >= $50K: +2
  • No top-tier audit on current version: +2
  • < 30 days since deploy: +1
  • Protocol you've hunted before: +1
  • Upgradeable proxies present: +1

Step 1: Accounting State Desynchronization (28% of Criticals)

# Find accounting variables
grep -rn "totalSupply\|totalShares\|totalAssets\|totalDebt\|cumulativeReward" contracts/

# Find ALL early returns in critical functions
grep -rn "\breturn\b" contracts/ -B3 | grep -B3 "if\b"

Check: For each early return in claim/redeem/withdraw functions:

  • Which state variables are updated in the normal path?
  • Are ALL of them also updated in the early return path?
  • If A updated but B isn't → potential desync bug

Step 2: Access Control (19% of Criticals)

# Sibling function families — do ALL have same modifier set?
grep -rn "function vote\|function poke\|function reset\|function update\|function claim\|function harvest" contracts/ -A2

# Ownership check: existence vs ownership
grep -rn "_requireOwned\|ownerOf\|_isApprovedOrOwner" contracts/ -B5

# Silent modifiers (if without revert)
grep -rn "modifier\b" contracts/ -A8 | grep -B3 "if (" | grep -v "require\|revert"

# Uninitialized proxy
grep -rn "function initialize\b" contracts/ -A3
grep -rn "_disableInitializers()" contracts/

Read the full file on GitHub · 217 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 217 lines · 0 tokens per session scan A c6202c7230a9

Subscribe to this mod's changes

web3-audit is a command published in the GitHub repository Zyrexnn/Cybermes (668 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,834 tokens. A static security scan graded it A with 0 findings. It is 98% identical to web3-audit, differing in 1 line, and is treated as a copy.