smart-contract-development

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). The skill's required workflow explicitly instructs the agent to query public on-chain endpoints and services (e.g., "use @vechain/mcp-server for on-chain data" in SKILL.md and ThorClient.at('https://testnet.vechain.org') / contract.read calls in references/smart-contracts.md), meaning it will fetch and interpret untrusted public blockchain data that can materially influence transaction building and tool actions.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 1.00). The skill is explicitly focused on blockchain development for VeChainThor and names VeChain-specific tooling for on-chain interaction and transaction building (e.g., "@vechain/mcp-server" for on-chain data and transaction building, deploying contracts with Hardhat, and references to signing, fee, and token-transfer implications). These are specific crypto/blockchain capabilities (transaction building/signing, deploy/interact with contracts, and handling VET/VTHO) rather than generic developer tools. That meets the "Crypto/Blockchain (Wallets, Swaps, Signing)" criterion for Direct Financial Execution.