Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Crypto Safety Pack

    1

    Verify on-chain safety, validate transaction claims, and reconcile x402 payments via direct RPC inspection.

    $19.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Crypto Safety Pack

    Crypto Safety Pack

    Example session with this skill installed

    Check if this address is safe to send 1.5 ETH to: 0x742d35Cc6634C0532925a3b844Bc454e4438f44e. I suspect it might be a delegated wallet.

    • Read your context and instructions
    • Compiled the crypto safety

    I have performed a pre-flight safety check on the provided address using public RPC data.

    Safety Check Verdict

    MetricResultDetails
    VERDICTTRAPHigh risk detected.
    Code Prefix0xef0100EIP-7702 delegated EOA trap detected.
    Delegate Target0x810b0c...Points to a known drainer contract pattern.
    Wallet AgeFreshLow transaction count and recent creation.
    AutomationDetectedAny ETH sent here is auto-forwarded to the delegate.

    Evidence:

    • eth_getCode call returned 0xef0100... indicating the account is controlled by a separate contract.
    • eth_getTransactionCount returned 0, increasing the likelihood of a disposable trap wallet.

    Next steps

    • Do not send any funds to this address as they will be immediately moved.
    • Revoke any existing approvals if you have interacted with the delegate target 0x810b0c... previously.
    • Check your own wallet for unauthorized EIP-7702 delegations using a security scanner.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    This package provides three specialized tools for verifying on-chain integrity across EVM and Solana networks. It addresses the high risk of interacting with unknown addresses, the difficulty of validating transaction claims without manual effort, and the complexity of automated x402 payment flows. The tools allow developers to automate safety checks for drainer patterns like EIP-7702, audit historical balances, and reconcile payment signatures against actual settlement logs.

    What it does

    • Safety screening identifies EIP-7702 delegation traps, honeypot tokens, and unlimited approval risks.
    • Claim verification confirms transaction receipts, balances, and contract storage state directly from RPC data.
    • Payment reconciliation validates x402 signatures and EIP-3009 authorizations against on-chain logs.
    • Risk assessment flags low-reputation fresh wallets and off-chain permit phishing history.

    How it works

    1. Identify targets by providing a wallet address, transaction hash, or x402 payment header to the agent.
    2. Fetch live data via read-only JSON-RPC methods like eth_getCode, eth_getLogs, and eth_call.
    3. Analyze findings to detect specific attack patterns or confirm that transferred amounts and recipients match the claim.

    Frameworks & tools

    The skills interface with EVM-compatible chains (Ethereum, Base, Arbitrum, Polygon) and Solana using public RPC endpoints.

    Why this beats prompting it yourself

    Generic prompts cannot reliably parse contract code for the 0xef0100 prefix or decode EIP-712 permit structures. This skill uses specific block-pinned reads to ensure data is accurate at the time of the event, preventing hallucinated balances.

    Use cases

    • Pre-flight safety checks before sending high-value transfers to unknown addresses.
    • Payment automation for agents serving resources behind an HTTP 402 paywall.
    • Audit verification to confirm user-reported transfers without manual block explorer searches.

    Known limitations

    Read-only verification only. Safe verdicts indicate no known patterns were found but do not guarantee future safety. Solana program-level logic is currently out of scope.

    Read-only. Safe verdicts do not guarantee future safety. Solana program-level logic is out of scope. Requires public RPC access.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    Requires

    Llamarpc

    Permissions

    Read Files
    Terminal / Shell
    Network Access

    Allowed Hosts

    eth.llamarpc.com

    Read-only by design: network access is used solely for public JSON-RPC reads (eth_call, eth_getBalance, eth_getCode, eth_getLogs) against public blockchain RPC endpoints (Ethereum, Base, BSC, Solana). Terminal runs the bundled Node.js check scripts. No API keys, no private keys, no transactions, no file writes outside the working folder.

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This skill protects agents from 'drainer' patterns like EIP-7702 delegation traps and honeypot tokens, while also automating the reconciliation of x402 payments to ensure services are only rendered for valid on-chain settlements.

    The skill is designed for EVM-compatible chains (including Ethereum, Base, Arbitrum, and Polygon) as well as Solana, utilizing public or private RPC endpoints to fetch live data.

    You will receive the pre-configured tool definitions, specialized logic for RPC data parsing, and documentation on how to integrate the safety and reconciliation tools into your existing AI agent workflow.

    No, this skill is strictly read-only; it inspects logs and balances to verify claims but does not have the permissions to sign transactions or move funds from your wallet.

    LLMs often hallucinate transaction details or fail to recognize complex exploit patterns in raw hex data; these tools use deterministic RPC calls to ensure your agent acts on verified, real-time blockchain state.

    New in Web3 & Crypto