Meme Coin Audit logo

Meme Coin Audit

OrganizationPopular
awarexone
meme-coin-audit

Meme coin and token security audit — rug pull detection (honeypot, hidden mint, fee manipulation, LP lock bypass), Solana SPL token analysis (freeze authority, mint authority, metadata mutability), Token-2022 extension risks (transfer hooks, permanent delegate), DEX liquidity pool attacks (sandwich amplification, LP drain, bonding curve exploits), pump.fun/Raydium/Jupiter integration risks, token_scanner.py automation, and real exploit examples from 2024-2025. Use for any token audit, rug pull assessment, meme coin security review, or pre-investment due diligence.

Overview

Publisherawarexone
RepositoryAgentic-Bug-Hunter
Skill namememe-coin-audit
Stars
4.9K
Forks
868
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by awarexone on GitHub. Read the source before you install it.

Installation

Install the Meme Coin Audit AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/awarexone/Agentic-Bug-Hunter.git /tmp/Agentic-Bug-Hunter
mkdir -p .claude/skills
cp -r /tmp/Agentic-Bug-Hunter/skills/meme-coin-audit .claude/skills/meme-coin-audit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Meme Coin Audit in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Meme Coin Audit on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Meme Coin Audit is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

MEME COIN & TOKEN SECURITY AUDIT

Fast-kill rug pull detection and deep token security analysis for EVM and Solana meme coins.


PRE-DIVE KILL SIGNALS

Check these BEFORE reading a single line of code. If any are true, skip the audit — the token is likely a rug or not worth the time.

Hard Kills (Skip Immediately)

  • Contract not verified on Etherscan/Solscan → Cannot audit source = cannot trust
  • Deployer wallet has history of rug pulls (check Etherscan deployer page)
  • Token age < 1 hour AND no known team → Too early, wait for more data
  • Mint authority retained (Solana) AND no cap → Infinite mint = certain rug
  • Freeze authority retained (Solana) on meme coin → Honeypot confirmed
  • Transfer hook present (Token-2022) with mutable hook program → Honeypot vector
  • Permanent delegate extension (Token-2022) → Can steal all holder tokens

Soft Kills (Proceed with Extreme Caution)

  • Top holder > 20% of supply (excluding DEX pools)
  • LP not burned or locked in verified contract
  • Contract is upgradeable / proxy with retained admin
  • Less than $5K liquidity in the pool
  • No social presence / anonymous deployer with no history

THE ONE RULE

"Check ALL authorities and owner functions. The retained authority IS the rug vector."

Every rug pull requires a privileged operation: mint, blacklist, fee change, LP removal, or authority abuse. If you find the privilege, you found the bug.


BUG CLASSES (8 TOKEN-SPECIFIC)

1. HIDDEN MINT / UNLIMITED SUPPLY

35% of meme coin rugs. Deployer mints tokens post-launch, dumps on LP.

Quick grep (EVM):

bash
grep -rn "function mint\|_mint(\|_balances\[.*\] +=" src/ --include="*.sol" | grep -v "test\|lib\|node_modules"

Quick grep (Solana):

bash
grep -rn "MintTo\|mint_to\|mint_authority" src/ --include="*.rs" | grep -v "test\|target"

Kill if: MAX_SUPPLY enforced in every mint path, or mint function removed entirely.

2. HONEYPOT / TRANSFER RESTRICTION

25% of meme coin scams. Buy works, sell blocked.

Quick grep:

bash
grep -rn "blacklist\|isBlacklisted\|_bots\|maxTxAmount\|approve.*override\|tradingEnabled" src/ --include="*.sol"

Solana equivalent:

bash
grep -rn "freeze_authority\|transfer_hook\|TransferHook\|permanent_delegate" src/ --include="*.rs"

Kill if: No blacklist mapping, no transfer hooks, no freeze authority.

3. FEE MANIPULATION

20% of rugs. Sell fee set to 99% after initial buys.

Quick grep:

bash
grep -rn "setFee\|setSellFee\|_taxFee\|_sellFee" src/ --include="*.sol"
grep -rn "function set.*Fee" -A5 src/ --include="*.sol" | grep -v "require\|MAX\|<="

Kill if: Fee setter has require(fee <= MAX_FEE) with MAX_FEE <= 10%.

4. LIQUIDITY POOL DRAIN

LP removal, migration, or manipulation to crash price.

Quick grep:

bash
grep -rn "migrateLP\|emergencyWithdraw\|\.sync()\|setPair\|setRouter" src/ --include="*.sol"

Kill if: LP tokens burned to dead address, no migration function, no pair setter.

5. BONDING CURVE MANIPULATION

Exploits in pump.fun-style bonding curves.

Quick grep:

bash
grep -rn "virtualReserve\|setCurve\|graduate\|bonding_curve" src/ --include="*.sol" --include="*.rs"

Kill if: Curve parameters immutable, graduation permissionless.

6. AUTHORITY RETENTION (SOLANA)

Retained mint/freeze/update authorities on Solana tokens.

Quick grep:

bash
grep -rn "mint_authority\|freeze_authority\|update_authority\|close_authority" src/ --include="*.rs"
grep -rn "set_authority.*None" src/ --include="*.rs"  # Good sign: revocation

Kill if: All authorities = None, verified on-chain.

7. FAKE RENOUNCE / HIDDEN OWNERSHIP

Ownership appears renounced but backdoor control retained.

Quick grep:

bash
grep -rn "renounceOwnership.*override\|_shadowAdmin\|_backupOwner\|selfdestruct" src/ --include="*.sol"

Kill if: renounceOwnership NOT overridden, no second admin role, no selfdestruct.

8. SANDWICH AMPLIFICATION BY DESIGN

Contract makes holders maximally sandwichable.

Quick grep:

bash
grep -rn "swapExactTokensForETH" -A5 src/ --include="*.sol" | grep "0,"
grep -rn "swapThreshold\|_rebase\|mandatoryPool" src/ --include="*.sol"

Kill if: Auto-swap has proper slippage, no rebase mechanics.


AUTOMATED SCANNER

Run the token scanner tool for fast red flag detection:

bash
# EVM token
python3 tools/token_scanner.py contracts/Token.sol

# Solana program
python3 tools/token_scanner.py programs/token/ --chain solana --recursive

# Full directory scan with report
python3 tools/token_scanner.py src/ --recursive --output findings/token-report.md

The scanner checks all 8 bug classes via regex patterns. It catches:

  • Direct mint/balance manipulation
  • Blacklist and transfer restriction patterns
  • Unbounded fee setters
  • LP migration and emergency withdraw functions
  • Fake renounce overrides
  • Zero slippage auto-swaps
  • All Solana authority patterns
  • Token-2022 dangerous extensions

Scanner does NOT check:

  • On-chain state (use Etherscan/Solscan for authority verification)
  • Holder distribution (use DEXTools/Birdeye)
  • LP lock status (use Unicrypt/PinkLock/Solscan)
  • Deployer wallet history (manual check)

FOUNDRY POC TEMPLATE (TOKEN EXPLOITS)

solidity
// SPDX-License-Identifier: MIT
pragma solidity ^0.8.0;

import "forge-std/Test.sol";
import "../src/Token.sol";

contract TokenExploitTest is Test {
    Token token;
    address owner = makeAddr("owner");
    address victim = makeAddr("victim");
    address attacker = makeAddr("attacker");

    // Uniswap V2 router (mainnet fork)
    address constant ROUTER = 0x7a250d5630B4cF539739dF2C5dAcb4c659F2488D;
    address constant WETH = 0xC02aaA39b223FE8D0A0e5C4F27eAD9083C756Cc2;

    function setUp() public {
        vm.createSelectFork("mainnet");
        // Deploy token as owner
        vm.startPrank(owner);
        token = new Token();
        // Add liquidity...
        vm.stopPrank();
    }

    function test_hiddenMint_rug() public {
        // Step 1: Victim buys tokens
        vm.startPrank(victim);
        // ... buy tokens on Uniswap
        vm.stopPrank();

        // Step 2: Owner mints and dumps
        vm.startPrank(owner);
        uint256 supplyBefore = token.totalSupply();
        token.mint(owner, 1_000_000_000e18);
        assertGt(token.totalSupply(), supplyBefore, "Supply should increase");
        // ... sell minted tokens
        vm.stopPrank();

        // Step 3: Victim's tokens are now worthless
        // Assert token price crashed
    }

    function test_honeypot_blacklist() public {
        // Step 1: Victim buys
        vm.startPrank(victim);
        // ... buy tokens
        vm.stopPrank();

        // Step 2: Owner blacklists victim
        vm.startPrank(owner);
        token.blacklist(victim);
        vm.stopPrank();

        // Step 3: Victim cannot sell
        vm.startPrank(victim);
        vm.expectRevert("Blacklisted");
        token.transfer(address(1), 100e18);
        vm.stopPrank();
    }

    function test_fee_manipulation_rug() public {
        // Step 1: Verify initial fee is low
        assertEq(token.sellFee(), 3); // 3%

        // Step 2: Owner sets fee to 99%
        vm.prank(owner);
        token.setFees(3, 99); // Buy 3%, Sell 99%

        // Step 3: Victim sells — loses 99% to fees
        vm.startPrank(victim);
        uint256 balanceBefore = address(victim).balance;
        // ... sell tokens
        // Assert: received almost nothing
        vm.stopPrank();
    }
}

SOLANA QUICK CHECKS (NO SOURCE CODE NEEDED)

When you don't have source code, check on-chain:

1. MINT AUTHORITY → solana account <MINT> --output json | check mint_authority
   - Should be null
   - If Some(pubkey) → CRITICAL: can mint infinite tokens

2. FREEZE AUTHORITY → same as above, check freeze_authority
   - Should be null
   - If Some(pubkey) → CRITICAL: honeypot

3. LP STATUS → Check Raydium/Orca pool
   - LP burned? (tokens sent to 1111...1111)
   - LP locked? (in verified locker with no backdoor)
   - LP held by deployer? → CRITICAL: instant rug

4. TOP HOLDERS → Birdeye/Solscan holders tab
   - Top 10 < 30% of supply (excluding pools)
   - Creator wallets (check first transactions)

5. PROGRAM UPGRADEABILITY
   - Is the program upgradeable? → can change any logic
   - Upgrade authority should be None for immutable programs

6. TOKEN-2022 EXTENSIONS
   - Any transfer hook? → potential honeypot
   - Permanent delegate? → CRITICAL

FULL REFERENCE FILES

For deep dives into specific areas:

  • web3/10-meme-coin-bugs.md — All 8 bug classes with full code examples and variants
  • web3/11-solana-token-audit.md — Solana-specific: SPL authorities, Token-2022, pump.fun, Raydium, Jupiter
  • web3/12-dex-lp-attacks.md — DEX & LP manipulation patterns (sandwich, pool sniping, CL position attacks)

Frequently asked questions

What does the Meme Coin Audit AI skill do?

Meme coin and token security audit — rug pull detection (honeypot, hidden mint, fee manipulation, LP lock bypass), Solana SPL token analysis (freeze authority, mint authority, metadata mutability), Token-2022 extension risks (transfer hooks, permanent delegate), DEX liquidity pool attacks (sandwich amplification, LP drain, bonding curve exploits), pump.fun/Raydium/Jupiter integration risks, token_scanner.py automation, and real exploit examples from 2024-2025. Use for any token audit, rug pull assessment, meme coin security review, or pre-investment due diligence.

Why use Meme Coin Audit on TypingMind?

Because you install it once and use it with any model. Meme Coin Audit is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Meme Coin Audit in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/awarexone/Agentic-Bug-Hunter/tree/main/skills/meme-coin-audit. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Meme Coin Audit?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Meme Coin Audit?

As many as you like. As long as a model supports skills, you can use Meme Coin Audit with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Meme Coin Audit AI skill free?

Yes. It is published on GitHub by awarexone under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇