Agent skill

Audit Report Generation

by ccashwell in ccashwell/evm-cortex

A skill your agent uses when compiling final audit reports. An agent skill from ccashwell/evm-cortex.

MITAuto-check passedDocuments & Office

Install Audit Report Generation

skills CLI
$ npx skills add ccashwell/evm-cortex --skill audit-report-generation -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ccashwell/evm-cortex audit-report-generation --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ccashwell/evm-cortex.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/audit-report-generation .claude/skills/audit-report-generation && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
audit-report-generation
GitHub stars
131
Token cost
~2k tokens
SKILL.md length
131 words
Files
1
Skills in repo
89
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when compiling final audit reports. An agent skill from ccashwell/evm-cortex.

  • Compiling final audit reports
  • SKILL.md covers Report Structure, Report Template, Finding Format and Recommendations Section, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve Summarization

What it does

Audit Report Generation is an agent skill from ccashwell/evm-cortex. Use when compiling final audit reports. Covers executive summary, scope and methodology, finding format, severity classification, risk summary tables, recommendations, and appendices.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Documents & Office, covering Summarization. The repository describes itself as: Ethereum protocol engineering squad for AI coding assistants. The licence is MIT.

When your agent uses it

  • Compiling final audit reports
  • Tasks that involve Summarization

Example prompts

  • “/audit-report-generation”

What it can do on your machine

Read from SKILL.md and the folder at commit f8f3301. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown and solidity).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Audit Report Generation loads about 2k tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 131 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~52
When it runs · the whole SKILL.md, loaded when a task matches
~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ccashwell/evm-cortex at commit f8f3301, republished under its MIT licence (© ccashwell). 131 words, ~2,001 tokens.

Download SKILL.mdSave it as .claude/skills/audit-report-generation/SKILL.md (or your agent's skills folder).
name
audit-report-generation
description
Use when compiling final audit reports. Covers executive summary, scope and methodology, finding format, severity classification, risk summary tables, recommendations, and appendices.

Audit Report Generation

Report Structure

1. Executive Summary
2. Scope & Methodology
3. System Overview
4. Findings
5. Risk Summary
6. Recommendations
7. Appendices

Report Template

markdown
# Security Audit Report

## Protocol Name — Audit Report
**Audit Period**: YYYY-MM-DD to YYYY-MM-DD
**Commit**: abc1234
**Auditor(s)**: [Names]
**Report Version**: 1.0

---

## 1. Executive Summary

[Protocol Name] is a [brief description]. This audit reviewed [X] contracts
comprising [Y] SLOC deployed on [chain(s)].

### Results Summary

| Severity | Count | Fixed | Acknowledged | Open |
|----------|-------|-------|-------------|------|
| Critical | 0 | 0 | 0 | 0 |
| High | 1 | 1 | 0 | 0 |
| Medium | 3 | 2 | 1 | 0 |
| Low | 5 | 3 | 2 | 0 |
| Informational | 4 | 2 | 2 | 0 |
| **Total** | **13** | **8** | **5** | **0** |

### Overall Assessment

[1-2 paragraph summary of the security posture. Note the most significant
findings and the team's response. Mention code quality, test coverage,
and adherence to best practices.]

---

## 2. Scope & Methodology

### In-Scope Contracts

| Contract | SLOC | Risk Rating |
|----------|------|-------------|
| src/Vault.sol | 245 | High |
| src/Strategy.sol | 189 | Medium |
| src/Oracle.sol | 78 | Medium |
| src/Governance.sol | 156 | Low |
| **Total** | **668** | |

### Out of Scope
- Test files, deployment scripts
- Frontend / offchain infrastructure
- OpenZeppelin library code (v5.0.1)

### Methodology
1. **Recon** (Day 1): Automated analysis (Slither, Aderyn), architecture mapping
2. **Breadth** (Days 2-3): Systematic review of all functions and access controls
3. **Depth** (Days 4-6): Focused analysis on high-risk areas, PoC construction
4. **Verification** (Day 7): Finding verification, severity classification, report

### Tools Used
- Foundry (forge test, forge coverage)
- Slither v0.10.x
- Aderyn v0.x.x
- Manual review

---

## 3. System Overview

### Architecture
[Diagram or text description of contract relationships]

### Key Mechanisms
- **Deposits**: Users deposit USDC, receive vault shares
- **Yield**: Strategy deploys assets to Aave V3
- **Withdrawals**: Users redeem shares for USDC + yield
- **Governance**: Owner (multisig) controls strategy and parameters

### Trust Assumptions
- Owner multisig is honest and competent
- Chainlink oracle provides accurate, timely prices
- Aave V3 operates correctly

---

## 4. Findings

Finding Format

markdown
### [H-01] Share Inflation via First Depositor Attack

**Severity**: High
**Status**: Fixed (commit def5678)
**Category**: Logic Error

#### Description

The vault does not implement virtual shares or a minimum deposit,
allowing an attacker to inflate the share price and steal from
subsequent depositors.

The attacker deposits 1 wei to receive 1 share, then donates a large
amount directly to the vault. The next depositor's shares are rounded
down to 0, transferring their entire deposit to the attacker.

#### Affected Code

```solidity
// src/Vault.sol, line 45
function deposit(uint256 assets, address receiver) external returns (uint256 shares) {
    shares = assets * totalSupply() / totalAssets(); // rounds to 0 when totalAssets >> assets
    // ...
}
Impact

Any user depositing after the attacker loses their entire deposit. Requires the attacker to be the first depositor and front-run the second deposit.

Loss: Up to 100% of the victim's deposit.

Proof of Concept

See test/poc/PoCShareInflation.t.sol:

solidity
function test_PoC_firstDepositorShareInflation() public {
    // Attacker deposits 1 wei
    vm.prank(attacker);
    vault.deposit(1, attacker);

    // Attacker donates to inflate price
    vm.prank(attacker);
    token.transfer(address(vault), 1_000_000e6);

    // Victim gets 0 shares
    vm.prank(victim);
    uint256 shares = vault.deposit(999_999e6, victim);
    assertEq(shares, 0); // VULNERABILITY: victim gets nothing
}
Recommendation

Implement virtual shares and virtual assets offset:

solidity
uint256 internal constant VIRTUAL_SHARES = 1e3;
uint256 internal constant VIRTUAL_ASSETS = 1;

function convertToShares(uint256 assets) public view returns (uint256) {
    return assets.mulDiv(totalSupply() + VIRTUAL_SHARES, totalAssets() + VIRTUAL_ASSETS);
}

## Risk Summary Table

```markdown
## 5. Risk Summary

| ID | Title | Severity | Status |
|----|-------|----------|--------|
| H-01 | Share inflation via first depositor | High | Fixed |
| M-01 | Oracle staleness check insufficient | Medium | Fixed |
| M-02 | Harvest sandwich attack | Medium | Acknowledged |
| M-03 | Missing withdrawal limit | Medium | Fixed |
| L-01 | Event parameter ordering incorrect | Low | Fixed |
| L-02 | Redundant approval in withdraw | Low | Acknowledged |
| L-03 | Missing zero-address check in constructor | Low | Fixed |
| L-04 | Floating pragma | Low | Fixed |
| L-05 | Centralization risk: owner can change strategy | Low | Acknowledged |
| I-01 | Use custom errors instead of strings | Info | Fixed |
| I-02 | Missing NatSpec on public functions | Info | Acknowledged |
| I-03 | Unused import in Strategy.sol | Info | Fixed |
| I-04 | Consider two-step ownership transfer | Info | Acknowledged |

Recommendations Section

markdown
## 6. Recommendations

### Short Term (before deployment)
1. Fix all Critical and High findings
2. Add invariant tests for core accounting
3. Implement emergency pause mechanism
4. Add monitoring for health factor degradation

### Medium Term (post-deployment)
1. Add time-delayed oracle fallback
2. Implement withdrawal queuing for large amounts
3. Deploy on testnet with full integration testing

### Long Term
1. Consider formal verification for core math
2. Implement decentralized governance (reduce multisig dependency)
3. Multiple oracle sources for price resilience

Appendices

markdown
## 7. Appendices

### A. Slither Output (Triaged)
[Filtered Slither results with true/false positive annotations]

### B. Test Coverage
| File | Lines | Branches | Functions |
|------|-------|----------|-----------|
| Vault.sol | 95% | 88% | 100% |
| Strategy.sol | 92% | 85% | 100% |

### C. Gas Report
[forge test --gas-report output for key functions]

### D. Verified Addresses
| Contract | Chain | Address |
|----------|-------|---------|
| Vault | Mainnet | 0x... |
| Strategy | Mainnet | 0x... |

Severity Definitions

Include these definitions in every report:

markdown
### Severity Definitions

**Critical**: Direct theft of funds, permanent protocol bricking, or
              privilege escalation to admin-level access.

**High**:     Significant loss of funds (>1% TVL), temporary protocol DoS
              lasting >24h, or conditions leading to critical with
              additional steps.

**Medium**:   Moderate fund loss, griefing attacks, temporary DoS,
              value leakage over time, or governance manipulation.

**Low**:      Minor issues, gas inefficiencies, best practice violations
              with edge-case security implications.

**Informational**: Code quality, readability, best practices with no
                   direct security impact.

Checklist

  • Executive summary with results table
  • Scope definition with SLOC counts
  • Methodology section describing audit approach
  • System overview with architecture and trust assumptions
  • Each finding has: severity, status, description, impact, PoC, recommendation
  • Risk summary table with all findings
  • Recommendations section (short/medium/long term)
  • Appendices with tool output and coverage data
  • Severity definitions included
  • Report reviewed for clarity and accuracy before delivery
  • Fix review performed on resolved findings

© ccashwell, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/audit-report-generation of ccashwell/evm-cortex.

Open the folder on GitHubat commit f8f3301

Compare with similar skills

Audit Report Generation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Audit Report Generation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Audit Report Generation this skillccashwell/evm-cortex131—~2kAutomated safety check: PassMIT
HTML Summarytestdouble/han279—~2.9kAutomated safety check: PassMIT
Quant Paper ExtractorCamusGIT/EvoQuant151—~2.4kAutomated safety check: PassApache-2.0
Document Groundinggaotiexinqu/OneResearchClaw450—~2kAutomated safety check: PassMIT
Read Bookcoreyhaines31/makerskills850—~2.2kAutomated safety check: PassMIT
Executive Dashboard Generatormanojbajaj95/claude-gtm-plugin1052 repos~3.4kAutomated safety check: PassMIT

Similar skills

  • HTML Summary

    testdouble/han

    Convert a stakeholder summary markdown file into a single self-contained HTML executive report — bottom line and decision asks up front, supporting detail later — styled with a Test Double-derived…

    279 GitHub stars~2.9k tokensUpdated 7 days ago
    Documents & OfficeAuto-check passed
  • Quant Paper Extractor

    CamusGIT/EvoQuant

    Convert quantitative research report PDFs to markdown, then extract structured knowledge (paperId, title, year, source, keywords, tldr, abstract, strategy, method, experiment, result) into JSONL…

    151 GitHub stars~2.4k tokensUpdated 1 mo ago
    Documents & OfficeAuto-check passed
  • Document Grounding

    gaotiexinqu/OneResearchClaw

    Convert a raw document into a structured grounding note for downstream research and summarization.

    450 GitHub stars~2k tokensUpdated 5 mo ago
    Documents & OfficeAuto-check passed
  • Read Book

    coreyhaines31/makerskills

    When you want to read and extract structured notes from a book — PDF, EPUB, MOBI, markdown, .txt, pasted text, or URL to a public-domain work.

    850 GitHub stars~2.2k tokensUpdated today
    Documents & OfficeAuto-check passed
  • Executive Dashboard Generator

    manojbajaj95/claude-gtm-plugin

    Transform raw data from CSVs, Google Sheets, or databases into executive-ready reports with visualizations, key metrics, trend analysis, and actionable recommendations.

    105 GitHub starsUsed in 2 repos~3.4k tokens
    Documents & OfficeAuto-check passed
  • Chat Complex Documents

    vellum-ai/vellum-assistant

    Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source.

    1.4k GitHub stars~1.5k tokensUpdated today
    Documents & OfficeAuto-check passed

More from ccashwell/evm-cortex

All 89 skills in this repo
  • Xray Pre Audit

    ccashwell/evm-cortex

    A skill your agent uses when preparing for a security audit, performing reconnaissance on a new codebase, or creating a protocol overview.

    131 GitHub stars~25k tokensUpdated 9 days ago
    Auto-check passed
  • Aave Integration

    ccashwell/evm-cortex

    A skill your agent uses when integrating with Aave V3 for lending, borrowing, flash loans, or building on top of Aave markets.

    131 GitHub stars~1.3k tokensUpdated 9 days ago
    Auto-check passed
  • Access Control Patterns

    ccashwell/evm-cortex

    Access control design patterns for Solidity protocols. An agent skill from ccashwell/evm-cortex.

    131 GitHub stars~1.8k tokensUpdated 9 days ago
    Auto-check passed
  • Anvil Patterns

    ccashwell/evm-cortex

    A skill your agent uses when running a local Ethereum node with Anvil.

    131 GitHub stars~1.3k tokensUpdated 9 days ago
    Auto-check passed
  • Audit Breadth Scan

    ccashwell/evm-cortex

    A skill your agent uses when performing systematic breadth-first review of all contracts during a security audit.

    131 GitHub stars~1.4k tokensUpdated 9 days ago
    Auto-check passed
  • Audit Depth Analysis

    ccashwell/evm-cortex

    A skill your agent uses when performing deep analysis of specific findings or high-risk areas during a security audit.

    131 GitHub stars~1.6k tokensUpdated 9 days ago
    Auto-check passed

Questions about Audit Report Generation

What does Audit Report Generation do?

A skill your agent uses when compiling final audit reports. An agent skill from ccashwell/evm-cortex. Audit Report Generation is an agent skill from ccashwell/evm-cortex. Use when compiling final audit reports.

When should I use Audit Report Generation?

Audit Report Generation fits situations like: compiling final audit reports; tasks that involve Summarization.

How do I install Audit Report Generation in Claude Code?

Run `npx skills add ccashwell/evm-cortex --skill audit-report-generation -a claude-code`. Or copy the skill folder (skills/audit-report-generation in ccashwell/evm-cortex) into .claude/skills/audit-report-generation in your project. Claude Code loads it when a task matches its description.

How do I install Audit Report Generation in Codex?

Run `npx skills add ccashwell/evm-cortex --skill audit-report-generation -a codex`. Or copy the skill folder (skills/audit-report-generation in ccashwell/evm-cortex) into .agents/skills/audit-report-generation in your project. Codex loads it when a task matches its description.

Can I use Audit Report Generation in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ccashwell/evm-cortex --skill audit-report-generation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/audit-report-generation, .gemini/skills/audit-report-generation, .github/skills/audit-report-generation and .opencode/skills/audit-report-generation in your project.

What does Audit Report Generation need to run?

SKILL.md names no scripts, command-line tools or credentials: Audit Report Generation is instructions for the agent only.

Does Audit Report Generation access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Audit Report Generation safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Audit Report Generation use?

Audit Report Generation is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Audit Report Generation use?

About 2k tokens (SKILL.md is roughly 8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Audit Report Generation?

Skills that share tags, products or a category with Audit Report Generation: HTML Summary (testdouble/han, 279 stars), Quant Paper Extractor (CamusGIT/EvoQuant, 151 stars), Document Grounding (gaotiexinqu/OneResearchClaw, 450 stars) and Read Book (coreyhaines31/makerskills, 850 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Audit Report Generation?

ccashwell (a GitHub user) maintains it in ccashwell/evm-cortex, which has 131 GitHub stars. The repository holds 89 skills in this directory. The repository was last updated on September 30, 2026.

Source: ccashwell/evm-cortex on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.