secure-workflow-guide skill
✓ OfficialGuides smart contract security through a five-step process including Slither scans, feature validation, visual diagrams, and manual review.
- GitHub stars
- 8,136
- Files
- 5
- Last commit
- Nov 11, 2026
- License
- CC-BY-SA-4.0
- Allowed tools
- —
What does the secure-workflow-guide skill do?
secure-workflow-guide guides smart contract security through a five-step process including Slither scans, feature validation, visual diagrams, and manual review.
Summary generated from the skill's SKILL.md.
About the secure-workflow-guide skill
Securing smart contracts through a structured five-step process is what this skill enables for blockchain developers. It follows a specific methodology to enhance security during every check-in or before a final deployment. The process begins by running Slither scans to identify common vulnerabilities using over 70 built-in detectors, providing severity levels and fix recommendations.
After initial scans, the tool validates special features like upgradeability risks and ERC conformance. It produces visual security diagrams, including inheritance graphs and function summaries, to help identify shadowing or access control issues. Developers use this to document security properties for property-based fuzzing with Echidna or formal verification with Manticore. Finally, it guides manual reviews of complex areas such as front-running, cryptography, and DeFi interactions like oracle manipulation. This approach moves beyond simple bug hunting to provide a comprehensive security report and a prioritized action plan.
What an agent can do with it
- 1Perform a full security auditRun the complete five-step workflow to secure a smart contract from end to end.
- 2Prepare for formal verificationDocument critical security properties and invariants to set up advanced testing tools.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the secure-workflow-guide skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the secure-workflow-guide skill in Plugin
/plugin marketplace add trailofbits/skills /plugin install building-secure-contracts@trailofbits
Install the secure-workflow-guide skill in Claude Code
~/.claude/skills/secure-workflow-guide/SKILL.md
$ npx degit trailofbits/skills/plugins/building-secure-contracts/skills/secure-workflow-guide ~/.claude/skills/secure-workflow-guideInstall the secure-workflow-guide skill in Claude Code (project)
.claude/skills/secure-workflow-guide/SKILL.md
$ npx degit trailofbits/skills/plugins/building-secure-contracts/skills/secure-workflow-guide .claude/skills/secure-workflow-guideInstall the secure-workflow-guide skill in Codex
~/.agents/skills/secure-workflow-guide/SKILL.md
$ npx degit trailofbits/skills/plugins/building-secure-contracts/skills/secure-workflow-guide ~/.agents/skills/secure-workflow-guideInstall the secure-workflow-guide skill in Gemini CLI
~/.gemini/skills/secure-workflow-guide/SKILL.md
$ npx degit trailofbits/skills/plugins/building-secure-contracts/skills/secure-workflow-guide ~/.gemini/skills/secure-workflow-guideInstall the secure-workflow-guide skill in Claude.ai
npx degit trailofbits/skills/plugins/building-secure-contracts/skills/secure-workflow-guide secure-workflow-guide && zip -r secure-workflow-guide.zip secure-workflow-guide # claude.ai → Customize → Skills → + → Create skill → Upload a skill → secure-workflow-guide.zip
Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A skill needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachabletrailofbits/skills/plugins/building-secure-contracts/skills/secure-workflow-guide is public and reachablegithub.com/trailofbits/skills/tree/HEAD/plugins/building-sec ↗Pass
- Open source license (OSI)CC-BY-SA-4.0 is not OSI-approvedspdx.org/licenses/CC-BY-SA-4.0.html ↗Finding
- Commit or release in the last yearLast commit 2026-11-11github.com/trailofbits/skills/commits ↗Pass
- No download-and-run or credential theft in scriptsNo scripts in the skill folderPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/trailofbits/skills/blob/HEAD/plugins/building-sec ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/trailofbits/skills/blob/HEAD/plugins/building-sec ↗Pass
- SKILL.md follows the Agent Skills formatValid name and description; says when to use it; 162 linesgithub.com/trailofbits/skills/blob/HEAD/plugins/building-sec ↗Pass
SKILL.md
View on GitHubSecure Workflow Guide
Purpose
Guides through Trail of Bits' secure development workflow - a 5-step process to enhance smart contract security throughout development.
Use this: On every check-in, before deployment, or when you want a security review
The 5-Step Workflow
Covers a security workflow including:
Step 1: Check for Known Security Issues
Run Slither with 70+ built-in detectors to find common vulnerabilities:
- Parse findings by severity
- Explain each issue with file references
- Recommend fixes
- Help triage false positives
Goal: Clean Slither report or documented triages
Step 2: Check Special Features
Detect and validate applicable features:
- Upgradeability: slither-check-upgradeability (17 upgrade risks)
- ERC conformance: slither-check-erc (6 common specs)
- Token integration: Recommend token-integration-analyzer skill
- Security properties: slither-prop for ERC20
Note: Only runs checks that apply to your codebase
Step 3: Visual Security Inspection
Generate 3 security diagrams:
- Inheritance graph: Identify shadowing and C3 linearization issues
- Function summary: Show visibility and access controls
- Variables and authorization: Map who can write to state variables
Review each diagram for security concerns
Step 4: Document Security Properties
Help document critical security properties:
- State machine transitions and invariants
- Access control requirements
- Arithmetic constraints and precision
- External interaction safety
- Standards conformance
Then set up testing:
- Echidna: Property-based fuzzing with invariants
- Manticore: Formal verification with symbolic execution
- Custom Slither checks: Project-specific business logic
Note: Most important activity for security
Step 5: Manual Review Areas
Analyze areas automated tools miss:
- Privacy: On-chain secrets, commit-reveal needs
- Front-running: Slippage protection, ordering risks, MEV
- Cryptography: Weak randomness, signature issues, hash collisions
- DeFi interactions: Oracle manipulation, flash loans, protocol assumptions
Search codebase for these patterns and flag risks
For detailed instructions, commands, and explanations for each step, see WORKFLOW_STEPS.md.
How I Work
When invoked, I will:
- Explore your codebase to understand structure
- Run Step 1: Slither security scan
- Detect and run Step 2: Special feature checks (only what applies)
- Generate Step 3: Visual security diagrams
- Guide Step 4: Security property documentation
- Analyze Step 5: Manual review areas
- Provide action plan: Prioritized fixes and next steps
Adapts based on:
- What tools you have installed
- What's applicable to your project
- Where you are in development
Rationalizations (Do Not Skip)
| Rationalization | Why It's Wrong | Required Action |
|---|---|---|
| "Slither not available, I'll check manually" | Manual checking misses 70+ detector patterns | Install and run Slither, or document why it's blocked |
| "Can't generate diagrams, I'll describe the architecture" | Descriptions aren't visual - diagrams reveal patterns text misses | Execute slither --print commands, generate actual visual outputs |
| "No upgrades detected, skip upgradeability checks" | Proxies and upgrades are often implicit or planned | Verify with codebase search before skipping Step 2 checks |
| "Not a token, skip ERC checks" | Tokens can be integrated without obvious ERC inheritance | Check for token interactions, transfers, balances before skipping |
| "Can't set up Echidna now, suggesting it for later" | Property-based testing is Step 4, not optional | Document properties now, set up fuzzing infrastructure |
| "No DeFi interactions, skip oracle/flash loan checks" | DeFi patterns appear in unexpected places (price feeds, external calls) | Complete Step 5 manual review, search codebase for patterns |
| "This step doesn't apply to my project" | "Not applicable" without verification = missed vulnerabilities | Verify with explicit codebase search before declaring N/A |
| "I'll provide generic security advice instead of running workflow" | Generic advice isn't actionable, workflow finds specific issues | Execute all 5 steps, generate project-specific findings with file:line references |
Example Output
When I complete the workflow, you'll get a comprehensive security report covering:
- Step 1: Slither findings with severity, file references, and fix recommendations
- Step 2: Special feature validation results (upgradeability, ERC conformance, etc.)
- Step 3: Visual diagrams analyzing inheritance, functions, and state variable authorization
- Step 4: Documented security properties and testing setup (Echidna/Manticore)
- Step 5: Manual review findings (privacy, front-running, cryptography, DeFi risks)
- Action plan: Critical/high/medium priority tasks with effort estimates
- Workflow checklist: Progress on all 5 steps
For a complete example workflow report, see EXAMPLE_REPORT.md.
What You'll Get
Security Report:
- Slither findings with severity and fixes
- Special feature validation results
- Visual diagrams (PNG/PDF)
- Manual review findings
Action Plan:
- Critical issues to fix immediately
- Security properties to document
- Testing to set up (Echidna/Manticore)
- Manual areas to review
Workflow Checklist:
- Clean Slither report
- Special features validated
- Visual inspection complete
- Properties documented
- Manual review done
Getting Help
Trail of Bits Resources:
- Office Hours: Every Tuesday (schedule)
- Empire Hacking Slack: #crytic and #ethereum channels
Other Security:
- Remember: Security is about more than smart contracts
- Off-chain security (owner keys, infrastructure) equally critical
Ready to Start
Let me know when you're ready and I'll run through the workflow with your codebase!
Files in this skill
5secure-workflow-guide skill questions
How do I install the secure-workflow-guide skill in Claude Code?
Run npx degit trailofbits/skills/plugins/building-secure-contracts/skills/secure-workflow-guide ~/.claude/skills/secure-workflow-guide. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the secure-workflow-guide skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.