0xlayerghost/solidity-agent-kit/defi-security

Claude Code and agent skill by 0xlayerghost/solidity-agent-kit

Trust tier 2
  • community
LLM review pending
Source check pending

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

[AUTO-INVOKE] MUST be invoked BEFORE deploying DeFi contracts (DEX, lending, staking, LP, token). Covers anti-whale, anti-MEV, flash loan protection, launch checklists, and emergency response. Trigger: any deployment or security review of DeFi-related contracts.

Install

npx vskill@latest install 0xlayerghost/solidity-agent-kit/defi-security

SKILL.md

The same SKILL.md was published earlier as 0xlayerghost/solidity-agent-kit/defi-security.

DeFi Security Principles

Language Rule

  • Always respond in the same language the user is using. If the user asks in Chinese, respond in Chinese. If in English, respond in English.
Scope: Only applicable to DeFi projects (DEX, lending, staking, LP, yield). Non-DeFi projects can ignore this skill.

Protection Decision Rules

ThreatRequired Protection
Whale manipulationDaily transaction caps + per-tx amount limits + cooldown window
MEV / sandwich attackEOA-only checks (msg.sender == tx.origin), or use commit-reveal pattern
ArbitrageReferral binding + liquidity distribution + fixed yield model + lock period
ReentrancyReentrancyGuard on all external-call functions (see solidity-security skill)
Flash loan attackCheck block.number change between operations, or use TWAP pricing
Price manipulationChainlink oracle or TWAP — never rely on spot AMM reserves for pricing
Approval exploitUse safeIncreaseAllowance / safeDecreaseAllowance, never raw approve for user flows
Governance attackVoting requires snapshot + minimum token holding period; timelock ≥ 48h on proposal execution
ERC4626 inflation attackFirst deposit must enforce minimum amount or use virtual shares to prevent share dilution via rounding
Cross-vault trust bypassRouter/Registry relay must verify vault authorization; never trust caller identity inside flash loan callbacks — EVMbench/noya H-08
Collateral ownership exploitLiquidation/staking operations must verify actual NFT/collateral ownership — EVMbench/benddao
Bonding curve manipulationID/pricing params in create operations must be fully determined before external calls — EVMbench/phi H-06
DEX pair _transfer TOCTOUNever distinguish operation type by balance/reserve checks in _transfer — both directions are exploitable: buy vs removeLiquidity (pair→user) and sell vs addLiquidity (user→pair); use address whitelist only; new projects prefer Uniswap V4 Hook
Per-address state bypassAny mapping(address => ...) restriction (cooldown, max tx, max balance) can be bypassed via multi-address or transfer-then-trade; propagate restriction state on wallet-to-wallet transfers using max(_lastTxTime[to], _lastTxTime[from]) — never block.timestamp (griefing) or direct assignment (overwrite shortening)

Anti-Whale Implementation Rules

  • Maximum single transaction amount: configurable via onlyOwner setter
  • Daily cumulative limit per address: track with mapping(address => mapping(uint256 => uint256)) (address → day → amount)
  • Cooldown between transactions: enforce minimum time gap with block.timestamp check
  • Whitelist for exempt addresses (deployer, LP pair, staking contract)

Flash Loan Protection Rules

  • For price-sensitive operations: require that block.number has changed since last interaction
  • For oracle-dependent calculations: use time-weighted average (TWAP) over minimum 30 minutes
  • For critical state changes: add minimum holding period before action (e.g., must hold tokens for N blocks)

Protocol Composability Risks

Source: EVMbench (OpenAI/Paradigm, Feb 2026) — vulnerability patterns from Code4rena audits
  • Cross-vault operations [noya H-08]: Registry/Router relay calls must verify vault-level authorization; prevent keeper from using flash loan to impersonate other vaults
  • Lending collateral [benddao]: Liquidation functions must verify msg.sender actually owns or is authorized to operate on target collateral
  • Bonding curve [phi H-06]: In create + auto-buy operations, ID assignment and pricing params must be fully determined before the buy transaction executes; prevent reentrancy from modifying them
  • Shared registries [noya H-08]: Permission propagation chains in shared registries must be verified hop-by-hop; never rely solely on "trusted sender" flags

Launch Checklist

Before mainnet deployment, verify all items:

  • [ ] All onlyOwner functions transferred to multisig wallet
  • [ ] Timelock contract deployed and configured (minimum 24h delay for critical changes)
  • [ ] Emergency pause mechanism tested — both pause and unpause functions work correctly
  • [ ] Daily limit parameters documented and set to reasonable values
  • [ ] Third-party security audit completed and all critical/high findings resolved
  • [ ] Testnet deployment running for minimum 7 days with no issues
  • [ ] Slippage, fee, and lock period parameters reviewed and documented
  • [ ] Initial liquidity plan documented (amount, lock duration, LP token handling)
  • [ ] Fuzz testing passes with high iterations (10000+) on all DeFi-critical functions

Emergency Response Procedure

StepAction
1. DetectMonitor alerts trigger (on-chain monitoring, community reports)
2. PauseDesignated address calls pause() — must respond within minutes
3. AssessTechnical lead analyzes root cause, estimates fund impact
4. CommunicatePost incident notice to community channels (Discord, Twitter, Telegram)
5. FixDeploy fix or prepare recovery plan
6. ResumeCall unpause() after fix verified on fork — or migrate to new contract
7. Post-mortemPublish detailed incident report within 48 hours

DeFi Testing Reference

Test ScenarioApproach
Fuzz test fund flowsRun fuzz tests on staking/pool contracts with high iterations (10000+)
Fork mainnet testingUse Foundry fork mode against mainnet RPC to test with real state
Simulate whale transactionUse Foundry cast CLI to simulate large-amount calls on a forked network

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationFailed, 75 of 100Degrading. 1 run. Evaluated 8 months ago.

Source

Popularity

Repository stars
4
Repository forks
1
7-day trend score
5

Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 11 May 2026, 6 months ago.

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/0xlayerghost/solidity-agent-kit/defi-security/badge)](https://verified-skill.com/skills/0xlayerghost/solidity-agent-kit/defi-security)

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