79yuuki/dotfiles/smart-contract-audit
Claude Code and agent skill by 79yuuki/dotfiles
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Audit Solidity smart contracts for loss-of-funds vulnerabilities, access-control bugs, economic attacks, upgradeability risks, and integration hazards. Use for authorized smart-contract security reviews before deployment or merge.
Install
npx vskill@latest install 79yuuki/dotfiles/smart-contract-auditSKILL.md
Smart Contract Audit
Audit Solidity smart contracts for high-severity (loss-of-funds) vulnerabilities using the EVMbench detect methodology.
Workflow
- Identify target: Get the path to the Solidity source directory (or single file).
- Install tools (if needed): Ensure
slitheris available. Runscripts/setup_tools.shif not installed. - Run static analysis: Execute
scripts/run_slither.sh <target_dir>to get initial findings. - Deep manual audit: Read all in-scope Solidity files. Focus on:
- Reentrancy (cross-function, read-only, cross-contract)
- Access control (missing modifiers, privilege escalation)
- Oracle manipulation (price feeds, TWAP)
- Integer overflow/underflow (unchecked blocks)
- Flash loan attack vectors
- Logic errors in state transitions
- Token handling (approval race, double-spend, fee-on-transfer)
- Upgradability issues (storage collisions, uninitialized proxies)
- Generate report: Write
submission/audit.mdin the EVMbench JSON format (see references/report-format.md). - Validate: Run
scripts/validate_report.py submission/audit.mdto ensure JSON is parseable.
Scope Rules
- In scope: Solidity source files, library dependencies used in business logic
- Out of scope: Test files, deployment scripts, configuration, unless user explicitly requests
- Trusted roles: Assume owner/admin/governance are trusted. Do NOT report privilege abuse by trusted roles.
- Severity: Only report HIGH severity (loss-of-funds). Skip medium/low/informational.
Output
Final report goes to submission/audit.md as a JSON code block. See references/report-format.md for the exact schema.
Tools
- Slither: Static analysis (setup via
scripts/setup_tools.sh) - Manual review: Deep code reading for logic bugs slither misses
References
references/report-format.md— Output JSON schema and examplesreferences/vulnerability-patterns.md— Common vulnerability patterns checklist
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingclaude/skills/smart-contract-audit/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/79yuuki/dotfiles/smart-contract-audit)