solidity-auditor
Skill16 starsChanged 10 months agoMITView on GitHub
Professional-grade Solidity smart contract security auditor. Performs comprehensive audits or targeted reviews (security vulnerabilities, gas optimization, storage optimization, code architecture, DeFi protocol analysis). Use this skill when users request smart contract audits, security reviews, vulnerability assessments, gas/storage optimization analysis, code quality reviews, or when analyzing Solidity code for any security or quality concerns. Supports all Solidity versions with version-specific vulnerability detection. Based on OWASP Smart Contract Top 10 (2025) and real-world exploit patterns.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- chasebrownn/claude-skillstheir own version, first seen Oct 15, 2026
- Gabson0x/bountyforgetheir own version, first seen Sep 16, 2026
- DROOdotFOO/agent-skillstheir own version, first seen Sep 1, 2026
- conjure-3301/skillstheir own version, first seen Aug 17, 2026
- sanbir/solidity-auditor-skillstheir own version, first seen Mar 8, 2026
- pashov/skillstheir own version, first seen Mar 4, 2026
Used with
Projects with it also use x-ray.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
pashovSkillx-ray
Generates an x-ray.md pre-audit report covering overview, enhanced threat model (protocol-type profiling, git-weighted attack surfaces, temporal risk analysis, composability dependency mapping), invariants, integrations, docs quality, test analysis, and developer/git history. Triggers on 'x-ray', 'audit readiness', 'readiness report', 'pre-audit report', 'prep this protocol', 'protocol prep', 'summarize this protocol'.
Also in 3 projects that use this
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- pashov/skills★ 1.3ksame name
- Gabson0x/bountyforge★ 431same name
- sanbir/solidity-auditor-skills★ 34same name
- DROOdotFOO/agent-skills★ 1same name
- chasebrownn/claude-skills★ 0same name
- conjure-3301/skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository8 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- geo-aeo-optimizationSkill
- install-skillSkill
- linkedin-personal-brandingSkill
- linkedin-roastSkill
- seo-content-auditSkill
- seo-technical-auditSkill
- suno-music-creatorSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 27
Identify Solidity Version: Check pragma statement. Read references/version-specific.md for version-specific considerations:
- Distinctive: line 35
Document entry points (external/public functions)
- Distinctive: line 37
Gather Context: Ask if not provided:
- Very specific: line 59
Read references/security-checklist.md and evaluate each category:
- Very specific: line 84
Use the template in references/report-template.md to structure findings.
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Solidity Smart Contract Auditor
A professional-grade smart contract audit skill covering security vulnerabilities, gas optimization, storage patterns, and code architecture. Adapted to Solidity version specifics.
Audit Types
Determine the audit type based on user request:
| User Request | Audit Type | Primary Reference |
| "Full audit", "comprehensive review" | Full Audit | All references |
| "Security audit", "vulnerability scan" | Security Focused | references/security-checklist.md |
| "Gas optimization", "reduce gas costs" | Gas Optimization | references/gas-optimization.md |
| "Storage optimization", "storage patterns" | Storage Optimization | references/storage-optimization.md |
| "Code review", "architecture review" | Architecture Review | references/architecture-review.md |
| "DeFi audit", "protocol review" | DeFi Protocol | Security + Architecture references |
Core Audit Workflow
Phase 1: Preparation
- Identify Solidity Version: Check pragma statement. Read
references/version-specific.mdfor version-specific considerations:- Pre-0.8.0: Check for SafeMath usage, arithmetic vulnerabilities
- 0.8.0+: Review
uncheckedblocks, check custom errors usage
- Understand Scope:
- List all contracts, interfaces, libraries
- Identify external dependencies (OpenZeppelin, etc.)
- Note inheritance hierarchy
- Document entry points (external/public functions)
- Gather Context: Ask if not provided:
- Protocol purpose and intended behavior
- Deployment chain(s)
- Expected user flows
- Admin roles and privileges
Phase 2: Static Analysis
- Run automated checks mentally using patterns from the security checklist:
- Access control patterns
- State-changing operations flow (checks-effects-interactions)
- External call patterns
- Arithmetic operations (especially in
uncheckedblocks)
- Map attack surface:
- External/public functions
- Functions handling ETH/tokens
- Functions with access control
- Upgrade mechanisms
Phase 3: Vulnerability Assessment
Read references/security-checklist.md and evaluate each category:
Critical Priority (check first):
- Access Control Vulnerabilities (OWASP SC-01) - $953M+ in losses
- Logic Errors (OWASP SC-02) - $64M+ in losses
- Reentrancy (OWASP SC-03) - $36M+ in losses
High Priority: 4. Flash Loan Attack Vectors (OWASP SC-04) 5. Input Validation (OWASP SC-05) 6. Oracle Manipulation (OWASP SC-06) 7. Unchecked External Calls (OWASP SC-07)
Medium Priority: 8. Integer Overflow/Underflow (version-dependent) 9. Denial of Service vectors 10. Front-running vulnerabilities
Phase 4: Optimization Analysis (if requested)
For gas optimization: Read references/gas-optimization.md
For storage optimization: Read references/storage-optimization.md
Phase 5: Report Generation
Use the template in references/report-template.md to structure findings.
Severity Classification
| Severity | Criteria | Action |
| Critical | Direct fund loss possible, no user interaction needed | Immediate fix required, do not deploy |
| High | Fund loss possible with specific conditions, significant impact | Must fix before deployment |
| Medium | Limited impact, unlikely exploitation, or governance issue | Should fix, assess risk |
| Low | Minor issue, best practice violation | Recommended fix |
| Informational | Code quality, gas optimization, suggestions | Optional improvement |
Quick Reference: Top Attack Vectors (2024-2025)
From OWASP Smart Contract Top 10 (2025) with real losses:
- Access Control ($953.2M): Missing/incorrect modifiers, exposed admin functions
- Logic Errors ($63.8M): Flawed business logic, incorrect calculations
- Reentrancy ($35.7M): State updates after external calls
- Flash Loans ($33.8M): Price manipulation, governance attacks
- Input Validation ($14.6M): Missing bounds checks, unchecked parameters
- Oracle Manipulation ($8.8M): TWAP manipulation, stale prices
Output Guidelines
Always provide:
- Clear finding title with severity
- Location: Contract name, function, line numbers
- Description: What the issue is
- Impact: Potential consequences
- Proof of Concept: How it could be exploited (when applicable)
- Recommendation: Specific fix with code example
Format recommendations as actionable code changes when possible.
Reference Files
Load these as needed based on audit type:
references/security-checklist.md- Complete vulnerability checklist with detection patternsreferences/gas-optimization.md- Gas optimization techniques and patternsreferences/storage-optimization.md- Storage layout and optimizationreferences/architecture-review.md- Code architecture best practicesreferences/version-specific.md- Solidity version considerationsreferences/report-template.md- Professional audit report template
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.