skills/report-writer/SKILL.md
Generate professional audit reports with structured findings, severity classifications, proof-of-concept code, and actionable recommendations. Use when writing individual findings, composing full audit reports, or formatting results for Code4rena, Sherlock, or client engagements.
npx skillsauth add 0x-shashi/web3-audit-skills skills/report-writerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
4 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Generate professional audit reports with structured findings, severity classifications, proof-of-concept code, and actionable recommendations. Based on industry standards from Trail of Bits, OpenZeppelin, Cyfrin, Spearbit, and Code4rena.
| Component | Purpose | Length | |-----------|---------|--------| | Executive Summary | Non-technical overview for stakeholders | 1-2 paragraphs | | Scope | Files/contracts reviewed, commit hash, exclusions | Table | | Methodology | How the audit was conducted | 1 paragraph | | Finding Summary | Table of all findings by severity | Table | | Detailed Findings | Full write-up of each finding | Per finding | | Centralization Risks | Admin/owner privilege analysis | Section | | Gas Optimizations | Optional efficiency improvements | List | | Appendix | Tools used, out-of-scope items | Section |
Based on the industry-standard Likelihood × Impact matrix:
| | Low Impact | Medium Impact | High Impact | |---|---|---|---| | High Likelihood | Medium | High | Critical | | Medium Likelihood | Low | Medium | High | | Low Likelihood | Info | Low | Medium |
| Level | Criteria | |-------|----------| | High | Exploitable by anyone, no special conditions, low cost | | Medium | Requires specific conditions, timing, or moderate skill | | Low | Requires unlikely conditions, high cost, or privileged access |
| Level | Criteria | |-------|----------| | High | Direct loss of funds, protocol takeover, permanent DoS | | Medium | Conditional fund loss, temporary DoS, incorrect state | | Low | Inconvenience, minor gas waste, edge case behavior |
| Prefix | Severity | Example | |--------|----------|----------| | C | Critical | C-01, C-02 | | H | High | H-01, H-02 | | M | Medium | M-01, M-02 | | L | Low | L-01, L-02 | | I | Informational | I-01, I-02 | | G | Gas Optimization | G-01, G-02 |
Specific title — Describes the vulnerability, not just the location
Clear description — A reader unfamiliar with the code can understand the issue
Precise location — Contract name, function, line numbers
Demonstrated impact — Concrete scenario showing what an attacker achieves
Working PoC — For Critical/High, a test case that proves exploitability
Actionable fix — Specific code change, not "fix the issue"
development
Systematically hunt for every variant of a discovered vulnerability across the entire codebase. Use when a bug is found and all instances of the same root cause pattern must be identified, or when performing variant analysis during competitive audits on Code4rena or Sherlock.
testing
Use when the user wants to audit TON smart contracts for security vulnerabilities, scan FunC or Tact contracts for message chain replay, bounce handling, or gas issues, review TON DeFi protocols for actor-model concurrency flaws, or analyze asynchronous message passing security.
tools
Analyze ERC20/ERC721/ERC1155 token implementations for non-standard behavior, fee-on-transfer mechanics, rebasing logic, blacklists, pausability, and integration risks. Use when reviewing protocols that interact with external tokens or implementing token-related features.
testing
Use when the user wants to audit Sui Move smart contracts, scan Sui-specific patterns including object ownership, shared objects, or dynamic fields, review Sui DeFi protocols for object model security issues, or analyze Sui-specific transaction and consensus patterns.