Skip to content

Blockchain Contract Attack

Guides the agent through smart contract audits and DeFi/bridge attack-surface checks using common tools.

Stars
8,323
Licence
Apache-2.0
Files
1 file

What it does

This skill gives an AI agent a checklist of blockchain and smart contract weaknesses to look for, such as reentrancy, missing access control, oracle price manipulation via flash loans, weak randomness, and risky token approvals. It also points the agent to tools like Slither and Mythril for static analysis and to the Etherscan API for pulling verified contract source code. It is written as a penetration-testing reference, so the agent is primed to think like an attacker when reviewing contracts, DeFi protocols, cross-chain bridges, and exposed blockchain RPC endpoints.

Great for

  • Security auditors reviewing Solidity smart contracts before deployment
  • Penetration testers assessing DeFi protocols or blockchain infrastructure they are authorized to test
  • Developers who want a quick checklist of common smart contract vulnerabilities

Skip it if

  • Attacking live contracts or protocols you do not own or have written permission to test, since the content is attack-oriented and misuse could cause real financial loss
  • Beginners looking for a complete audit: the file is a short list of keywords and techniques, not a step-by-step methodology, so it will not replace a professional review

Try asking

  • “Audit this Solidity contract for reentrancy and access control issues: [paste source or Etherscan address]”
  • “Pull the verified source of this contract from Etherscan and run Slither on it”
  • “Check whether this DeFi lending protocol is vulnerable to flash loan oracle manipulation”
  • “Review our exposed RPC node on port 8545 for unauthenticated eth_sendTransaction access”
Step-by-step guide: how to use Blockchain Contract AttackInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the Apache-2.0 licence and an attribution note.

    blockchain-contract-attack.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip blockchain-contract-attack.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip blockchain-contract-attack.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Give the agent the contract address or source code plus the chain it runs on, so it can fetch the verified source and tailor checks.
  • State explicitly that you are authorized to test the target, and ask for findings with severity and remediation rather than exploit payloads.
  • Run Slither or Mythril yourself and ask the agent to triage the results against the checklist, which keeps conclusions grounded in tool output.

What's inside

  • SKILL.md

Redistributed unmodified from AIPentest/CyberStrikeAI under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.