audit
Perform a smart contract security audit using the SCAR methodology.
Skill by jcvernaleo
Chalk Labs
Need help deploying audit?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/jcvernaleo-audit
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, security
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 1, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/audit
Tools it pre-approves 4
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Bash(git*),Read,Write
What's inside
- Skill name
audit- Description
- Perform a smart contract security audit using the SCAR methodology.
- License
- ISC
- Allowed tools
- Bash(git, *),, Read,, Write
- Instructions
- 176 lines in SKILL.md · view on GitHub
Before installing
- Pre-approves some shell commands
Files (1)
- SKILL.md
SKILL.md (first lines)
Perform a smart contract security audit using the SCAR methodology on $ARGUMENTS. ## Role You are a senior smart contract security auditor. Your task is to identify vulnerabilities, assess severity, and recommend fixes for all Solidity contracts in scope. ## Methodology: SCAR Follow this sequence for every audit: 1. **Scan** all in-scope contracts for known vulnerability patterns 2. **Classify** each finding by severity (Critical/High/Medium/Low/Info) 3. **Analyze** Critical and High findings with execution path tracing 4. **Report** all findings in the structured format below ## Vulnerability Checklist Scan for these patterns in every contract: - [ ] Reentrancy (state changes after external calls, cross-function, read-only) - [ ] Access control (missing modifiers, unprotected init, privilege escalation) - [ ] Unchecked external calls (low-level .call without return value checks) - [ ] Integer issues (unchecked blocks, unsafe casting between types) - [ ] Oracle manipulation (spot price dependencies, short TWAP windows) - [ ] Front-running (sandwich-vulnerable operations, predictable state outcomes) - [ ] Denial of service (unbounded loops, block gas limit, grief vectors) - [ ] Timestamp dependence (block.timestamp manipulation) - [ ] tx.origin authentication - [ ] Delegatecall to untrusted contracts - [ ] Cross-contract interaction chains (trust assumption failures) ## Severity Definitions - **Critical**: Direct fund loss, no preconditions required - **High**: Fund loss with specific conditions, state corruption - **Medium**: Conditional loss, griefing, value leakage over time - **Low**: Best practice violations, no direct fund risk - **Informational**: Code quality, gas optimization, documentation gaps ## Report Format Keep the report concise. Scale the detail of each finding to its severity: | Severity | Description | Proof of concept | Recommended fix | Regression test | |---|---|---|---|---| | Critical / High | Full | Step-by-step | With code | Foundry test | | Medium | Full | Short | With code | Only if the PoC is not obvious | | Low | Brief | Brief numbered steps, only if needed to show the issue is real | One or two sentences; code only if a few lines | None | | Informational | — | — | — | — | Informational findings get no section of their own. They appear only as rows in the `## Informational` table (ID, location, issue, suggestion), with each cell a single short sentence or less. Every finding (all severities) gets an ID (`F-01`, `F-02`, …) and a row in the `## Findings Summary` table. Number Critical first, then High, Medium, Low, and Informational last. Do not include: - A description of what the contract does or how it is structured - A per-check verification table, or a walk through the vulnerability checklist item by item. The "Areas verified" list replaces both. - A closing summary, totals section, or "Top N recommendations" list. The Findings Summary table already covers this. ## Output File When the audit is complete, write the full report to a markdown file named `audit-<scope>-<date>.md` in the `audit/` directory, where `<scope>` is the base name of the file or directory audited (e.g. `Vault` for `contracts/Vault.sol` or `src` for `src/`) and `<date>` is the current date in `YYYYMMDD` format (e.g. `audit/audit-Vault-20260421.md`). Create the `audit/` directory if it does not exist. Before writing the file, run `git config user.email` to get the calling user's email for the Auditor field. The file must be structured as a professional audit report: ``` # Smart Contract Security Audit **Date:** YYYY-MM-DD **Auditor:** <git config user.email> & Claude (SCAR Methodology) **Scope:** <file or directory audited> **Repository:** <git remote origin URL> **Commit:** <full git commit hash> ## Executive Summary **Overall risk:** Critical / High / Medium / Low <2–4 sentences: the most important result and anything the reader must know. Do not describe what the contract does.> **Areas verified:** - <one line per area, at most about 6 bullets, e.g. "Access control on every external function", "All `unchecked` blocks are bounded"> ## Findings Summary | ID | Severity | Title | |----|----------|-------| | F-01 | High | ... | | F-02 | Low | ... | | F-03 | Informational | ... | ... ## Findings ### F-01 [HIGH] <Title> **Contract:** `...` **Function:** `...` **Lines:** ... **Description** ... **Proof of Concept** ... **Recommended Fix** ```solidity ... ``` **Regression Test**
From jcvernaleo/llm-scripts, ISC.
More from jcvernaleo/llm-scripts
- 0.581score
audit-report
jcvernaleo
Generate a combined PDF report from all audit markdown files.
SkillAFreshness: A★ 1Claude Code +9 - 0.494score
vuln-scan
jcvernaleo
Audit web application source code for common vulnerability classes (XSS, SQLi, SSRF, path traversal, command injection, insecure deserialization, etc.)
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
authz-review
jcvernaleo
Review web application route/endpoint definitions and business logic for broken access control, privilege escalation, and IDOR vulnerabilities
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
secrets-audit
jcvernaleo
Hunt for hardcoded secrets, credentials, API keys, tokens, and other sensitive values in source code and config files
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
new-workspace
jcvernaleo
Create a new multi-repo umbrella workspace in the current directory.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
depcheck
jcvernaleo
Review dependency manifest files for dangerous, deprecated, or vulnerable package patterns
SkillCFreshness: C★ 1Claude Code +9 - 0.488score
resume
jcvernaleo
Resume the project from saved state.
SkillCFreshness: C★ 1Claude Code +9 - 0.488score
save-session
jcvernaleo
Save the current session state.
SkillCFreshness: C★ 1Claude Code +9 - 0.488score
status
jcvernaleo
Show current project state without taking action.
SkillCFreshness: C★ 1Claude Code +9 - 0.488score
sessions
jcvernaleo
List recent session logs across all projects.
SkillCFreshness: C★ 1Claude Code +9 - 0.264score
sqli-deep
jcvernaleo
No description from the publisher yet.
SkillCFreshness: C★ 1Claude Code +9 - 0.264score
pre-audit
jcvernaleo
No description from the publisher yet.
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 9, 2026 (28 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- ISC
- Repository
- github.com/jcvernaleo/llm-scripts
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from jcvernaleo
- 0.581score
audit-report
jcvernaleo
Generate a combined PDF report from all audit markdown files.
SkillAFreshness: A★ 1Claude Code +9 - 0.494score
vuln-scan
jcvernaleo
Audit web application source code for common vulnerability classes (XSS, SQLi, SSRF, path traversal, command injection, insecure deserialization, etc.)
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
authz-review
jcvernaleo
Review web application route/endpoint definitions and business logic for broken access control, privilege escalation, and IDOR vulnerabilities
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
new-workspace
jcvernaleo
Create a new multi-repo umbrella workspace in the current directory.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
depcheck
jcvernaleo
Review dependency manifest files for dangerous, deprecated, or vulnerable package patterns
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
secrets-audit
jcvernaleo
Hunt for hardcoded secrets, credentials, API keys, tokens, and other sensitive values in source code and config files
SkillCFreshness: C★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get audit running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
audit skill. Agent Mart. https://agentmart.dev/skills/jcvernaleo-audit (last updated 2026-10-24)