Menu

Not in the top 1,000 by GitHub stars

greatpie/smart-contract-audit-skill

Claude CodeLegalSecurity

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

skills/smart-contract-audit/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

31b814206032 → 31b814206032

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 31b814206032

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 31b8142060329fb3cb2389988c010f774bd9dd14

git clone --filter=blob:none --no-checkout https://github.com/greatpie/smart-contract-audit-skill.git .hotskills/greatpie-smart-contract-audit-skill && git -C .hotskills/greatpie-smart-contract-audit-skill checkout --detach 31b8142060329fb3cb2389988c010f774bd9dd14 # Copy each selected skill directory from .hotskills/greatpie-smart-contract-audit-skill into .claude/skills/<skill-name>/
100GitHub stars
0stars in 7 days
1skill in this repository
0commits in 30 days

Heat

0.3
  • Star growth, last 7 daysNot available
  • Star growth, last 24 hoursNot available
  • Rank movement, last 7 daysNot available
  • Commits, last 30 daysNot available
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Oct 25, 2026Oct 25, 2026100

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

smart-contract-audit

When your agent uses it

Script-backed, out-of-box auditing workflow for Solidity/EVM repositories based on EVMbench detect/patch/exploit methodology. Use when asked to audit a smart contract repo from a URL or local path, auto-prepare the environment, find high-severity loss-of-funds vulnerabilities, validate exploitability, propose safe fixes, and deliver a structured report with exact code references.

What it loads into context

Frontmatter

84 tokens

Always available to the agent

SKILL.md

953 tokens

When the skill is activated

Reference documents

1,532 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. Overview
  2. Quick Start
  3. Script Behavior
  4. Audit Standard
  5. Quality Bar
  6. Expected Outputs

Scripts executed separately

  • scripts/audit.sh
  • scripts/bootstrap.sh
  • scripts/generate_exploit_scaffold.sh
  • scripts/lib.sh
  • scripts/run_detect.sh
  • scripts/run_exploit.sh
  • scripts/run_patch.sh
  • scripts/templates/foundry-exploit-template.sh
  • scripts/templates/hardhat-exploit-template.sh

Files

  • ../../.claude-plugin/marketplace.jsonasset667 bytes
  • SKILL.mdcore4,295 bytes
  • SKILL.mdcore4,295 bytes
  • SKILL.mdcore4,295 bytes
  • SKILL.mdcore4,295 bytes
  • references/benchmark-reality-checklist.mddoc2,081 bytes
  • references/evmbench-core.mddoc2,420 bytes
  • references/report-template.mddoc1,282 bytes
  • references/script-usage.mddoc1,384 bytes
  • scripts/audit.shruns2,893 bytes
  • scripts/bootstrap.shruns6,636 bytes
  • scripts/generate_exploit_scaffold.shruns4,620 bytes
  • scripts/lib.shruns3,374 bytes
  • scripts/run_detect.shruns3,366 bytes
  • scripts/run_exploit.shruns4,815 bytes
  • scripts/run_patch.shruns3,288 bytes
  • scripts/templates/foundry-exploit-template.shruns2,495 bytes
  • scripts/templates/hardhat-exploit-template.shruns2,685 bytes

No excerpt is shown for this license. Read the source on GitHub.

View the complete source on GitHub

Skills included

  • smart-contract-audit

Repository facts

License
No license detected
Created
Feb 21, 2026
Last pushed
Feb 21, 2026
Forks
0
Open issues
0
Project activity
Slowing

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 5, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 3 notes
  • skills/smart-contract-audit/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/smart-contract-audit/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/smart-contract-audit/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 42 signals by file

skills/smart-contract-audit/SKILL.md

  • Network accessline 27
    bash scripts/audit.sh \   --repo https://github.com/greatpie/smart-contract-audit-skill.git \
  • Network accessline 28
    --repo https://github.com/greatpie/smart-contract-audit-skill.git \
  • Network accessline 36
    bash scripts/bootstrap.sh --repo https://github.com/greatpie/smart-contract-audit-skill.git --branch main

skills/smart-contract-audit/references/script-usage.md

  • Network accessline 6
    bash scripts/audit.sh --repo https://github.com/greatpie/smart-contract-audit-skill.git --modes detect,patch
  • Network accessline 12
    bash scripts/bootstrap.sh --repo https://github.com/greatpie/smart-contract-audit-skill.git --branch main

skills/smart-contract-audit/scripts/audit.sh

  • Executable scriptline 1
    #!/usr/bin/env bash

skills/smart-contract-audit/scripts/bootstrap.sh

  • Executable scriptline 1
    #!/usr/bin/env bash
  • Dangerous shell operationline 88
    rm -rf "$TARGET_DIR"

skills/smart-contract-audit/scripts/generate_exploit_scaffold.sh

  • Executable scriptline 1
    #!/usr/bin/env bash
  • Network accessline 118
    async function main() {   const rpcUrl = process.env.RPC_URL || "http://127.0.0.1:8756";
  • Network accessline 119
    const rpcUrl = process.env.RPC_URL || "http://127.0.0.1:8756";

skills/smart-contract-audit/scripts/lib.sh

  • Executable scriptline 1
    #!/usr/bin/env bash
  • Network accessline 31
    local input="$1"   case "$input" in     http://*|https://*|git@*|ssh://*|*.git) return 0 ;;
  • Network accessline 32
    case "$input" in     http://*|https://*|git@*|ssh://*|*.git) return 0 ;;     *) return 1 ;;
  • Network accessline 33
    http://*|https://*|git@*|ssh://*|*.git) return 0 ;;

skills/smart-contract-audit/scripts/run_detect.sh

  • Executable scriptline 1
    #!/usr/bin/env bash

skills/smart-contract-audit/scripts/run_exploit.sh

  • Executable scriptline 1
    #!/usr/bin/env bash
  • Network accessline 80
    PID_FILE="$AUDIT_META_DIR/anvil.pid" ANVIL_LOG="$AUDIT_LOG_DIR/anvil.log" RPC_URL="http://127.0.0.1:$PORT"
  • Network accessline 82
    RPC_URL="http://127.0.0.1:$PORT"
  • Dangerous shell operationline 93
    rm -f "$PID_FILE"
  • Network accessline 103
    EXISTING_PID="$(cat "$PID_FILE")"   if kill -0 "$EXISTING_PID" >/dev/null 2>&1; then     log "Anvil already running (PID $EXISTING_PID) at $RPC_URL"
  • Network accessline 104
    if kill -0 "$EXISTING_PID" >/dev/null 2>&1; then     log "Anvil already running (PID $EXISTING_PID) at $RPC_URL"   else
  • Network accessline 105
    log "Anvil already running (PID $EXISTING_PID) at $RPC_URL"
  • Dangerous shell operationline 108
    rm -f "$PID_FILE"
  • Network accessline 112
    if [ ! -f "$PID_FILE" ]; then   log "Starting Anvil on $RPC_URL (chain-id=$CHAIN_ID)"
  • Network accessline 113
    log "Starting Anvil on $RPC_URL (chain-id=$CHAIN_ID)"
  • Dangerous shell operationline 125
    rm -f "$PID_FILE"
  • Network accessline 133
    EXPLOIT_ENV="$AUDIT_SUBMISSION_DIR/exploit-env.sh" {   printf 'export RPC_URL=%q\n' "$RPC_URL"
  • Network accessline 134
    {   printf 'export RPC_URL=%q\n' "$RPC_URL"   printf 'export CHAIN_ID=%q\n' "$CHAIN_ID"
  • Network accessline 135
    printf 'export RPC_URL=%q\n' "$RPC_URL"
  • Network accessline 143
    [ -f "$TX_SCRIPT" ] || die "tx script not found: $TX_SCRIPT"     log "Running tx script: $TX_SCRIPT"     RPC_URL="$RPC_URL" CHAIN_ID="$CHAIN_ID" ATTACKER_PK="$ATTACKER_PK" ATTACKER_ADDRESS="$ATTACKER_ADDRESS" \
  • Network accessline 144
    log "Running tx script: $TX_SCRIPT"     RPC_URL="$RPC_URL" CHAIN_ID="$CHAIN_ID" ATTACKER_PK="$ATTACKER_PK" ATTACKER_ADDRESS="$ATTACKER_ADDRESS" \     REPO_DIR="$AUDIT_REPO_DIR" FRAMEWORK="$AUDIT_FRAMEWORK" \
  • Network accessline 145
    RPC_URL="$RPC_URL" CHAIN_ID="$CHAIN_ID" ATTACKER_PK="$ATTACKER_PK" ATTACKER_ADDRESS="$ATTACKER_ADDRESS" \
  • Network accessline 159
    esac   log "Running built-in exploit template: $TEMPLATE"   RPC_URL="$RPC_URL" CHAIN_ID="$CHAIN_ID" ATTACKER_PK="$ATTACKER_PK" ATTACKER_ADDRESS="$ATTACKER_ADDRESS" \
  • Network accessline 160
    log "Running built-in exploit template: $TEMPLATE"   RPC_URL="$RPC_URL" CHAIN_ID="$CHAIN_ID" ATTACKER_PK="$ATTACKER_PK" ATTACKER_ADDRESS="$ATTACKER_ADDRESS" \     REPO_DIR="$AUDIT_REPO_DIR" FRAMEWORK="$AUDIT_FRAMEWORK" SKILL_SCRIPTS_DIR="$S
  • Network accessline 161
    RPC_URL="$RPC_URL" CHAIN_ID="$CHAIN_ID" ATTACKER_PK="$ATTACKER_PK" ATTACKER_ADDRESS="$ATTACKER_ADDRESS" \
  • Network accessline 170
    - RPC URL: \`$RPC_URL\`

skills/smart-contract-audit/scripts/run_patch.sh

  • Executable scriptline 1
    #!/usr/bin/env bash

skills/smart-contract-audit/scripts/templates/foundry-exploit-template.sh

  • Executable scriptline 1
    #!/usr/bin/env bash

skills/smart-contract-audit/scripts/templates/hardhat-exploit-template.sh

  • Executable scriptline 1
    #!/usr/bin/env bash
  • Access to secretsline 84
    [Credential-related source omitted]
  • Access to secretsline 85
    [Credential-related source omitted]

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Signal confidence: 42 facts

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeNativeManifest .claude-plugin/marketplace.json.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md skills/smart-contract-audit/SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md skills/smart-contract-audit/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md skills/smart-contract-audit/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md skills/smart-contract-audit/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md skills/smart-contract-audit/SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

You might also use

anthropics/claude-for-legal

A suite of plugins for legal workflows

9.9kGitHub stars

RevylAI/greenlight

Pre-submission compliance scanner for the Apple App Store and Google Play. Scans code, privacy manifests, Android manifests, and IPA/APK/AAB binaries against the review guidelines…

2.5kGitHub stars

zubair-trabzada/ai-legal-claude

AI Legal Assistant skill for Claude Code. Contract review, risk analysis, NDA generation, compliance auditing, negotiation strategy, and PDF reports — 14 skills, 5 parallel agents…

1.8kGitHub stars

Klotzkette/claude-fuer-deutsches-recht

⚠️ Experimentelle Skill-Sammlung für deutsches Recht (Arbeits-, Gesellschafts-, Insolvenz-, Datenschutz-, Prozessrecht u.a.) – inzwischen verbessert und im Alltag getestet, aber w…

1.8kGitHub stars

Sushegaad/Claude-Skills-Governance-Risk-and-Compliance

Claude Skills for Governance, Risk, & Compliance (GRC): Expert-level compliance guidance for ISO 27001, SOC 2, FedRAMP, GDPR, HIPAA, NIST CSF, PCI DSS, EU AI Act, ISO 42001, ISO 2…

1kGitHub stars

THUYRan/Legal-Skills-Chinese

Legal abductive reasoning skill for generating and evaluating the most reasonable explanatory hypotheses when evidence is incomplete or facts are ambiguous. Combines Mill’s five m…

951GitHub stars