flash-loan-attacks

flash-loan-attacks is a skill for Claude Code, Codex from ccashwell/evm-cortex. It costs 55 tokens per session (1,319 once invoked), scanned A, original, MIT.

A guide to flash-loan attack patterns in DeFi systems. Flash loans are temporary, collateral-free loans that must be repaid in the same transaction, and can give an attacker large temporary buying or voting power.

In plain words
What is it for?
Use it to review or design defenses for protocols involving governance, oracles, AMMs, or liquidity pools.
Why use it?
It helps developers identify how instant access to large capital can manipulate governance, price oracles, automated market makers, and liquidity pools.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to review or design defenses for protocols involving governance, oracles, AMMs, or liquidity pools.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ccashwell/evm-cortex/flash-loan-attacks
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add ccashwell/evm-cortex --skill flash-loan-attacks
Clone the repo
git clone --depth 1 https://github.com/ccashwell/evm-cortex

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for flash-loan-attacks

README.md
[![agentmods](https://agentmods.dev/badge/skills/ccashwell/evm-cortex/flash-loan-attacks/github.svg)](https://agentmods.dev/skills/ccashwell/evm-cortex/flash-loan-attacks)
Your own site
<a href="https://agentmods.dev/skills/ccashwell/evm-cortex/flash-loan-attacks"><img src="https://agentmods.dev/badge/skills/ccashwell/evm-cortex/flash-loan-attacks/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for flash-loan-attacks

Your own site · 80×15
<a href="https://agentmods.dev/skills/ccashwell/evm-cortex/flash-loan-attacks"><img src="https://agentmods.dev/badge/skills/ccashwell/evm-cortex/flash-loan-attacks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,319 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.01319
Opus 5.5 $0.00022 $0.00528
Sonnet 5.5 $0.00011 $0.00264
Haiku 4.5 $0.00006 $0.00132

Measured 1mo ago against content hash 2d2ecd4402ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

flash-loan-attacks scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/flash-loan-attacks/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Flash Loan Attacks

What Makes Flash Loans Dangerous

Flash loans allow borrowing unlimited capital with zero collateral, provided it's returned within the same transaction. This means any attack that's profitable with enough capital becomes free to execute.

Attack Pattern: Governance Manipulation

Borrow tokens → acquire voting power → pass malicious proposal → profit.

1. Flash borrow 10M governance tokens from Aave/dYdX
2. Delegate voting power to attacker
3. Create + vote on malicious proposal (if single-block voting)
4. Proposal executes: drain treasury / change parameters
5. Return flash loan

Defense: Snapshot-Based Voting

contract SafeGovernor {
    // Voting power is snapshotted at proposal creation block
    // Flash-borrowed tokens have no voting power for existing proposals
    function propose(...) external returns (uint256 proposalId) {
        uint256 snapshot = block.number; // or block.number - 1
        proposals[proposalId].snapshotBlock = snapshot;
        // ...
    }

    function castVote(uint256 proposalId, uint8 support) external {
        uint256 snapshot = proposals[proposalId].snapshotBlock;
        // Uses historical balance, not current
        uint256 weight = token.getPastVotes(msg.sender, snapshot);
        // ...
    }
}

Additional defenses:

  • Voting delay: require N blocks between proposal creation and voting start
  • Time-weighted voting: voting power based on average balance over time
  • Proposal threshold: minimum token holding period to create proposals

Attack Pattern: Oracle Manipulation

Borrow tokens → manipulate spot price → exploit protocol using stale/spot price.

1. Flash borrow large amount of token A
2. Swap token A → token B on a DEX, crashing A's spot price
3. Protocol reads spot price (or manipulable TWAP)
4. Borrow against token B using deflated A price as collateral
5. Swap back, restoring price
6. Return flash loan, keep profit

Defense: TWAP Oracles

Read the full file on GitHub · 180 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 180 lines · 55 tokens per session scan A 2d2ecd4402ab

Subscribe to this mod's changes

flash-loan-attacks is a skill published in the GitHub repository ccashwell/evm-cortex (131 stars, last pushed 17d ago), licensed MIT. It adds 55 tokens to every session and 1,319 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

sector-rotation

An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.

HKUDS/Vibe-Trading · 39 tokens

twitter-reader

Read Twitter/X for financial research through opencli: the user's home timeline, tweet search, trending topics, bookmarks, a user's recent tweets, threads, articles, profiles, followers and following, and notifications. Use this skill whenever the user wants to know what people are saying on Twitter/X or fintwit about…

himself65/finance-skills · 110 tokens

strategy-pivot-designer

Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.

tradermonty/claude-trading-skills · 28 tokens

energy-procurement

Codified expertise for electricity and gas procurement, tariff optimization, demand charge management, renewable PPA evaluation, and multi-facility energy cost management. Informed by energy procurement managers with 15+ years experience at large commercial and industrial consumers. Includes market structure analysis…

hashgraph-online/awesome-codex-plugins · 93 tokens

china-portfolio-monitoring

A monitoring framework for tracking the financial results, operating measures, strategic milestones, and risks of companies held by China-focused private-equity funds. It uses measures such as revenue growth, margins, debt, cash flow, and return on equity.

jwangkun/claude-for-financial-services-cn · 86 tokens

airdrop-hunting-guide

Guide to finding and qualifying for crypto airdrops — eligibility criteria, farming strategies, on-chain activity requirements, Sybil detection avoidance, and tracking tools. Use when helping users understand airdrops, check eligibility, or plan participation strategies.

nirholas/three.ws · 54 tokens