Agent skill

Reentrancy Pattern Analysis

by quillai-network in quillai-network/quillshield_skills

Systematically detects all reentrancy vulnerability variants in smart contracts — classic, cross-function, cross-contract, and read-only reentrancy.

MITAuto-check passedSecurity

Install Reentrancy Pattern Analysis

skills CLI
$ npx skills add quillai-network/quillshield_skills --skill reentrancy-pattern-analysis -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install quillai-network/quillshield_skills reentrancy-pattern-analysis --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/quillai-network/quillshield_skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/reentrancy-pattern-analysis/skills/reentrancy-pattern-analysis .claude/skills/reentrancy-pattern-analysis && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
reentrancy-pattern-analysis
GitHub stars
130
Token cost
~3.4k tokens
SKILL.md length
817 words
Files
3 (incl. references)
Skills in repo
11
Repo updated
First seen
Licence
MIT

At a glance

Systematically detects all reentrancy vulnerability variants in smart contracts — classic, cross-function, cross-contract, and read-only reentrancy.

  • Works in 3 steps: Call Graph Construction → CEI Violation Detection → Guard Coverage Verification
  • Auditing contracts that make external calls
  • SKILL.md covers When to Use, When NOT to Use, Core Concept: The CEI Invariant and The Five Reentrancy Variants, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Reentrancy Pattern Analysis is an agent skill from quillai-network/quillshield_skills. Systematically detects all reentrancy vulnerability variants in smart contracts — classic, cross-function, cross-contract, and read-only reentrancy. Builds call graphs, verifies CEI (Checks-Effects-Interactions) pattern compliance, traces state changes relative to external calls, and identifies callback vectors through ERC-777/ERC-1155 hooks. Use when auditing contracts that make external calls, transfer ETH or tokens, interact with callback-enabled standards, or have complex multi-contract architectures.

Its SKILL.md is about 3.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/case-studies.md` and `references/reentrancy-variants.md`).

It sits in Security, covering Smart contract auditing and Codebase onboarding. The repository describes itself as: Structured skills for smart contract security audits. Infers state invariants, detects semantic guard gaps, models flash loan + oracle attack chains, simulates adversarial… The licence is MIT.

When your agent uses it

  • Auditing contracts that make external calls
  • Interact with callback-enabled standards
  • Have complex multi-contract architectures

Example prompts

  • “/reentrancy-pattern-analysis”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Call Graph Construction
  2. CEI Violation Detection
  3. Guard Coverage Verification

What it can do on your machine

Read from SKILL.md and the folder at commit 8bdd3c0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are solidity and markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Reentrancy Pattern Analysis loads about 3.4k tokens when it runs, and up to ~8.1k if it reads all its reference files. Until then it costs about 135 tokens; SKILL.md has 817 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~135
When it runs · the whole SKILL.md, loaded when a task matches
~3.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~8.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from quillai-network/quillshield_skills at commit 8bdd3c0, republished under its MIT licence (© quillai-network). 817 words, ~3,435 tokens.

Download SKILL.mdSave it as .claude/skills/reentrancy-pattern-analysis/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
reentrancy-pattern-analysis
description
Systematically detects all reentrancy vulnerability variants in smart contracts — classic, cross-function, cross-contract, and read-only reentrancy. Builds call graphs, verifies CEI (Checks-Effects-Interactions) pattern compliance, traces state changes relative to external calls, and identifies callback vectors through ERC-777/ERC-1155 hooks. Use when auditing contracts that make external calls, transfer ETH or tokens, interact with callback-enabled standards, or have complex multi-contract architectures.

Reentrancy Pattern Analysis

Systematically detect all variants of reentrancy vulnerabilities by mapping the relationship between external calls and state changes across the entire contract system.

When to Use

  • Auditing any contract that makes external calls (ETH transfers, token interactions, cross-contract calls)
  • Reviewing contracts integrating with callback-enabled token standards (ERC-777, ERC-1155)
  • Analyzing DeFi protocols with multi-contract architectures
  • Verifying reentrancy guard coverage across all entry points
  • When traditional tools only check for classic reentrancy but miss cross-function or read-only variants

When NOT to Use

  • Pure state variable analysis without external calls (use state-invariant-detection)
  • Access control consistency checking (use semantic-guard-analysis)
  • Full multi-dimensional audit (use behavioral-state-analysis, which orchestrates this skill)

Core Concept: The CEI Invariant

Checks-Effects-Interactions (CEI) is the fundamental safety pattern:

1. CHECKS   — Validate all conditions (require statements, access control)
2. EFFECTS  — Update all state variables
3. INTERACTIONS — Make external calls (ETH transfers, token calls, cross-contract)

Any function that performs INTERACTIONS before completing all EFFECTS is potentially vulnerable to reentrancy.

The Five Reentrancy Variants

Variant 1: Classic Single-Function Reentrancy

The original and most well-known pattern. A function makes an external call before updating its own state, allowing the callee to re-enter the same function.

solidity
// VULNERABLE
function withdraw(uint256 amount) public {
    require(balances[msg.sender] >= amount);
    (bool success, ) = msg.sender.call{value: amount}(""); // INTERACTION before EFFECT
    require(success);
    balances[msg.sender] -= amount; // State update AFTER external call
}

Detection: Find functions where state writes to variables used in require checks occur AFTER external calls.

Variant 2: Cross-Function Reentrancy

Two or more functions share state, and an attacker re-enters through a DIFFERENT function than the one making the external call.

solidity
function withdraw(uint256 amount) public {
    require(balances[msg.sender] >= amount);
    (bool success, ) = msg.sender.call{value: amount}("");
    require(success);
    balances[msg.sender] -= amount;
}

// Attacker re-enters HERE during withdraw's external call
function transfer(address to, uint256 amount) public {
    require(balances[msg.sender] >= amount);
    balances[msg.sender] -= amount;
    balances[to] += amount;
}

Detection: For each external call in function F, check if any OTHER public function reads/writes the same state variables that F modifies after the call.

Variant 3: Cross-Contract Reentrancy

The re-entry occurs through a different contract that shares state or trust relationships with the vulnerable contract.

solidity
// Contract A
function withdrawFromVault() public {
    uint256 shares = vault.balanceOf(msg.sender);
    vault.burn(msg.sender, shares);
    // External call — attacker can re-enter Contract B
    (bool success, ) = msg.sender.call{value: shares * pricePerShare}("");
    require(success);
}

// Contract B (attacker re-enters here)
function borrow() public {
    uint256 collateral = vault.balanceOf(msg.sender); // Reads stale state!
    // Shares not yet burned, so collateral appears inflated
    uint256 loanAmount = collateral * maxLTV;
    token.transfer(msg.sender, loanAmount);
}

Detection: Map all cross-contract dependencies. For each external call, identify which other contracts read the state that should have been updated.

Variant 4: Read-Only Reentrancy

A view/pure function returns stale state during a reentrancy callback. No state is modified during re-entry — the attacker exploits the READING of inconsistent state by a third-party contract.

solidity
// Pool contract
function removeLiquidity() external {
    uint256 shares = balances[msg.sender];
    // Burns LP tokens (updates internal accounting)
    _burn(msg.sender, shares);
    // External call BEFORE updating reserves
    (bool success, ) = msg.sender.call{value: ethAmount}("");
    // Reserves updated AFTER the call
    totalReserves -= ethAmount;
}

// This view function returns stale data during the callback
function getRate() public view returns (uint256) {
    return totalReserves / totalSupply(); // totalReserves not yet updated!
}

// Third-party contract reads the inflated rate
function priceOracle() external view returns (uint256) {
    return pool.getRate(); // Returns wrong value during reentrancy
}

Detection: For each external call, identify view functions that read state variables modified AFTER the call. Check if any external protocol depends on those view functions.

Variant 5: ERC-777 / ERC-1155 Callback Reentrancy

Token standards with built-in callback hooks that execute arbitrary code on the receiver during transfers.

solidity
// ERC-777: tokensReceived() hook called on recipient
// ERC-1155: onERC1155Received() hook called on recipient
// ERC-721: onERC721Received() hook called on recipient

function deposit(uint256 amount) public {
    token.transferFrom(msg.sender, address(this), amount); // Triggers callback!
    // If token is ERC-777, msg.sender's tokensReceived() runs HERE
    balances[msg.sender] += amount; // State update after callback
}

Detection: Identify all token transfer/transferFrom/safeTransfer calls. Check if the token could be ERC-777/ERC-1155/ERC-721. Verify state updates happen before the transfer.

Three-Phase Detection Architecture

Phase 1: Call Graph Construction

Build a complete map of all external interactions.

For each function, extract:

Function: withdraw()
├── External Calls:
│   ├── msg.sender.call{value: amount}("") at line 45
│   ├── token.transfer(user, amount) at line 48
│   └── oracle.getPrice() at line 42
├── State Writes:
│   ├── balances[msg.sender] -= amount at line 50
│   └── totalWithdrawn += amount at line 51
├── State Reads (in requires):
│   └── balances[msg.sender] at line 41
└── Modifiers:
    └── nonReentrant: NO

Call Classification:

Call TypeReentrancy RiskExamples
ETH transfer via callHIGHaddr.call{value: x}("")
Token transfer/transferFromMEDIUM-HIGHERC-777 hooks, ERC-1155 callbacks
safeTransferFrom (NFT)MEDIUMERC-721 onERC721Received callback
Cross-contract function callMEDIUMotherContract.doSomething()
staticcall / view callsLOWCannot modify state but can trigger read-only reentrancy in callers
delegatecallHIGHExecutes in caller's context
Phase 2: CEI Violation Detection

For each function with external calls, verify CEI ordering.

Algorithm:

For each function F with external calls:
  1. E = set of all state variables written by F
  2. C = set of all state variables read in require/if checks
  3. I = position of each external call in F
  4. For each external call at position P:
     a. W_after = state writes that occur AFTER position P
     b. If W_after ∩ (E ∪ C) ≠ ∅:
        → CEI VIOLATION: state modified after external call
     c. Classify violation:
        - W_after ∩ C ≠ ∅ → Classic reentrancy (check variable modified after call)
        - W_after ∩ E ≠ ∅ → State inconsistency window

Cross-Function Extension:

For each external call in function F at position P:
  W_before = state variables NOT yet updated at position P
  For each OTHER public function G:
    R_G = state variables read by G
    W_G = state variables written by G
    If R_G ∩ W_before ≠ ∅ OR W_G ∩ W_before ≠ ∅:
      → CROSS-FUNCTION REENTRANCY: G can be called during F's external call
         with inconsistent state
Show full SKILL.md (355 more words)Show less
Phase 3: Guard Coverage Verification

Check that reentrancy protections are correctly applied.

Guard Types:

GuardCoverageLimitations
nonReentrant modifier (OpenZeppelin)Single contract, all functions with modifierDoes not protect cross-contract reentrancy
CEI pattern compliancePer-functionMust be verified for every function individually
transfer() / send() (2300 gas)Limits callback gasNOT safe — EIP-1884 changed gas costs; don't rely on this
Pull payment patternEliminates external calls from state changesRequires architectural change

Verification:

For each function F with CEI violations:
  1. Check if F has nonReentrant modifier → Mitigated (single-contract only)
  2. Check if ALL functions sharing state also have nonReentrant → Mitigated (cross-function)
  3. Check if cross-contract consumers are protected → Requires manual review
  4. If no guard → VULNERABLE

Workflow

Task Progress:
- [ ] Step 1: Identify all external calls in every function (ETH transfers, token calls, cross-contract)
- [ ] Step 2: Build call graph with state read/write positions relative to each call
- [ ] Step 3: Detect CEI violations (state writes after external calls)
- [ ] Step 4: Detect cross-function reentrancy (shared state across functions)
- [ ] Step 5: Detect callback vectors (ERC-777, ERC-1155, ERC-721 token interactions)
- [ ] Step 6: Detect read-only reentrancy (view functions reading stale state)
- [ ] Step 7: Verify guard coverage (nonReentrant, CEI compliance, pull patterns)
- [ ] Step 8: Score findings and generate report

Output Format

markdown
## Reentrancy Analysis Report

### Finding: [Title]

**Function:** `functionName()` at `Contract.sol:L42`
**Variant:** [Classic | Cross-Function | Cross-Contract | Read-Only | Callback]
**Severity:** [CRITICAL | HIGH | MEDIUM]
**Guard Status:** [Unguarded | Partially Guarded | Guarded]

**CEI Violation:**
  - External call at line [X]: `[call expression]`
  - State write AFTER call at line [Y]: `[state variable] = [expression]`

**Re-Entry Path:**
  1. Attacker calls `functionName()`
  2. External call triggers callback to attacker contract
  3. Attacker re-enters via `[re-entry function]`
  4. State variable `[name]` still has pre-update value
  5. [Exploit consequence]

**Impact:**
[Funds drained, state corrupted, price manipulated, etc.]

**Recommendation:**
[Specific fix — reorder state updates, add nonReentrant, use pull pattern]

Severity Classification

VariantState ModifiedFunds at RiskSeverity
Classic — ETH drainYesYesCRITICAL
Cross-function — balance manipulationYesYesCRITICAL
Cross-contract — oracle/price manipulationIndirectlyYesHIGH
Read-only — stale price in third-partyNo (view only)PossiblyHIGH
Callback — ERC-777 deposit inflationYesPossiblyHIGH
Any variant with nonReentrant on targetMitigatedNoLOW/INFO

Advanced Detection: Transitive Reentrancy

Trace reentrancy through multiple contract hops:

Contract A calls Contract B
Contract B calls Contract C
Contract C calls back to Contract A (or reads A's stale state)

Detection: Build transitive call graph across all contracts in scope.
For each call chain A → B → ... → X:
  If X can call back to any contract in the chain → TRANSITIVE REENTRANCY

Quick Detection Checklist

When analyzing a contract, immediately check:

  • Does any function make an external call (ETH transfer, token transfer, cross-contract) BEFORE completing all state updates?
  • Are there multiple public functions that modify the same state variables, where at least one makes an external call?
  • Does the contract interact with ERC-777, ERC-1155, or ERC-721 tokens (callback hooks)?
  • Do view functions read state that is only partially updated during an external call?
  • Is nonReentrant applied to ALL functions that share state with a function making external calls, not just the calling function itself?
  • Does the contract rely on transfer() or send() for reentrancy protection? (Unsafe assumption)

For detailed variant taxonomy, see {baseDir}/references/reentrancy-variants.md. For real-world case studies, see {baseDir}/references/case-studies.md.

Rationalizations to Reject

  • "We use transfer() so reentrancy is impossible" → EIP-1884 changed gas costs; transfer is no longer considered safe
  • "The function has nonReentrant" → Check cross-function and cross-contract paths; one modifier doesn't protect everything
  • "It's just a view function" → Read-only reentrancy can manipulate prices and oracles in third-party contracts
  • "We only interact with standard ERC20 tokens" → ERC-777 is backward-compatible with ERC20; token type may change
  • "The external call is to a trusted contract" → Trust boundaries shift; verify the actual code path through all intermediaries
  • "State is updated right after the call" → "Right after" is too late; the call already happened

© quillai-network, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in plugins/reentrancy-pattern-analysis/skills/reentrancy-pattern-analysis of quillai-network/quillshield_skills.

  • SKILL.md
  • references/case-studies.md
  • references/reentrancy-variants.md

Open the folder on GitHubat commit 8bdd3c0

Compare with similar skills

Reentrancy Pattern Analysis next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Reentrancy Pattern Analysis compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Reentrancy Pattern Analysis this skillquillai-network/quillshield_skills130—~3.4kAutomated safety check: PassMIT
Ethereum Smart Contract Vulnerability Analysistradecatlabs/vibe-coding-cn17k1 repos~738Automated safety check: PassApache-2.0
Algorand Vulnerability Scannertrailofbits/skills7.4k—~3.1kAutomated safety check: PassCC-BY-SA-4.0
Cairo Vulnerability Scannertrailofbits/skills7.4k—~3.3kAutomated safety check: PassCC-BY-SA-4.0
Code Maturity Assessortrailofbits/skills7.4k—~1.8kAutomated safety check: PassCC-BY-SA-4.0
Cosmos Vulnerability Scannertrailofbits/skills7.4k—~2.7kAutomated safety check: PassCC-BY-SA-4.0

Similar skills

  • Runs Slither and Mythril against Solidity contracts to find reentrancy, overflow and access-control bugs before mainnet deployment, then triages and reports findings.

    17k GitHub starsUsed in 1 repo~738 tokens
    SecurityAuto-check passed
  • Official

    Scans Algorand TEAL and PyTeal contracts for 11 known vulnerability patterns, such as unchecked rekeying and fees, and reports each with severity and a fix.

    7.4k GitHub stars~3.1k tokensUpdated 2 days ago
    SecurityAuto-check passed
  • Cairo Vulnerability Scanner

    trailofbits/skills

    Official

    Scans Cairo and StarkNet contracts for 6 vulnerability patterns, including felt252 overflow, L1 to L2 messaging faults, address conversion and signature replay.

    7.4k GitHub stars~3.3k tokensUpdated 2 days ago
    SecurityAuto-check passed
  • Code Maturity Assessor

    trailofbits/skills

    Official

    Scores a smart contract or blockchain codebase across 9 maturity categories with evidence, then delivers a scorecard and a priority-ordered improvement roadmap.

    7.4k GitHub stars~1.8k tokensUpdated 2 days ago
    SecurityAuto-check passed
  • Official

    Scans Cosmos SDK modules and CosmWasm contracts for consensus-critical flaws that can halt a chain, lose funds or diverge state, using parallel scanning agents.

    7.4k GitHub stars~2.7k tokensUpdated 2 days ago
    SecurityAuto-check passed
  • Secure Workflow Guide

    trailofbits/skills

    Official

    Guides through Trail of Bits' 5-step secure development workflow.

    7.4k GitHub stars~1.7k tokensUpdated 2 days ago
    SecurityAuto-check passed

More from quillai-network/quillshield_skills

All 11 skills in this repo
  • Behavioral State Analysis

    quillai-network/quillshield_skills

    Token-efficient smart contract security auditing via Behavioral State Analysis (BSA).

    130 GitHub stars~1.4k tokensUpdated 6 mo ago
    Auto-check passed
  • Dos Griefing Analysis

    quillai-network/quillshield_skills

    Detects Denial of Service and griefing vulnerabilities in smart contracts.

    130 GitHub stars~3.3k tokensUpdated 6 mo ago
    Auto-check passed
  • External Call Safety

    quillai-network/quillshield_skills

    Detects unsafe external call patterns and token integration vulnerabilities in smart contracts.

    130 GitHub stars~3.1k tokensUpdated 6 mo ago
    Auto-check passed
  • Input Arithmetic Safety

    quillai-network/quillshield_skills

    Detects input validation failures and arithmetic vulnerabilities in smart contracts.

    130 GitHub stars~3.1k tokensUpdated 6 mo ago
    Auto-check passed
  • Oracle Flashloan Analysis

    quillai-network/quillshield_skills

    Detects price oracle manipulation and flash loan attack vectors in DeFi smart contracts.

    130 GitHub stars~2.8k tokensUpdated 6 mo ago
    Auto-check passed
  • Proxy Upgrade Safety

    quillai-network/quillshield_skills

    Detects vulnerabilities in upgradeable proxy smart contracts including storage layout collisions, uninitialized implementations, function selector clashing, delegatecall context issues, and upgrade…

    130 GitHub stars~3.2k tokensUpdated 6 mo ago
    Auto-check passed

Questions about Reentrancy Pattern Analysis

What does Reentrancy Pattern Analysis do?

Systematically detects all reentrancy vulnerability variants in smart contracts — classic, cross-function, cross-contract, and read-only reentrancy. Reentrancy Pattern Analysis is an agent skill from quillai-network/quillshield_skills. Systematically detects all reentrancy vulnerability variants in smart contracts — classic, cross-function, cross-contract, and read-only reentrancy.

When should I use Reentrancy Pattern Analysis?

Reentrancy Pattern Analysis fits situations like: auditing contracts that make external calls; interact with callback-enabled standards; have complex multi-contract architectures.

How do I install Reentrancy Pattern Analysis in Claude Code?

Run `npx skills add quillai-network/quillshield_skills --skill reentrancy-pattern-analysis -a claude-code`. Or copy the skill folder (plugins/reentrancy-pattern-analysis/skills/reentrancy-pattern-analysis in quillai-network/quillshield_skills) into .claude/skills/reentrancy-pattern-analysis in your project. Claude Code loads it when a task matches its description.

How do I install Reentrancy Pattern Analysis in Codex?

Run `npx skills add quillai-network/quillshield_skills --skill reentrancy-pattern-analysis -a codex`. Or copy the skill folder (plugins/reentrancy-pattern-analysis/skills/reentrancy-pattern-analysis in quillai-network/quillshield_skills) into .agents/skills/reentrancy-pattern-analysis in your project. Codex loads it when a task matches its description.

Can I use Reentrancy Pattern Analysis in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add quillai-network/quillshield_skills --skill reentrancy-pattern-analysis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/reentrancy-pattern-analysis, .gemini/skills/reentrancy-pattern-analysis, .github/skills/reentrancy-pattern-analysis and .opencode/skills/reentrancy-pattern-analysis in your project.

What does Reentrancy Pattern Analysis need to run?

SKILL.md names no scripts, command-line tools or credentials: Reentrancy Pattern Analysis is instructions for the agent only.

Does Reentrancy Pattern Analysis access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Reentrancy Pattern Analysis safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Reentrancy Pattern Analysis use?

Reentrancy Pattern Analysis is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Reentrancy Pattern Analysis use?

About 3.4k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.7k tokens, read only when the agent opens those files.

What are the alternatives to Reentrancy Pattern Analysis?

Skills that share tags, products or a category with Reentrancy Pattern Analysis: Ethereum Smart Contract Vulnerability Analysis (tradecatlabs/vibe-coding-cn, 17k stars), Algorand Vulnerability Scanner (trailofbits/skills, 7.4k stars), Cairo Vulnerability Scanner (trailofbits/skills, 7.4k stars) and Code Maturity Assessor (trailofbits/skills, 7.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Reentrancy Pattern Analysis?

quillai-network (a GitHub organization) maintains it in quillai-network/quillshield_skills, which has 130 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on March 30, 2026.

Source: quillai-network/quillshield_skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.