nad-wallet

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt instructs scripts to output and users/agents to set NAD_PRIVATE_KEY inline (e.g., export NAD_PRIVATE_KEY="0x..."/NAD_PRIVATE_KEY="0x..." node ... and create-wallet.js --env emitting env lines), which requires including raw private-key values verbatim in commands or outputs and thus poses secret-exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The skill's nadmail-register.js script explicitly fetches an authentication message from the public NadMail API (https://api.nadmail.ai/api/auth/start), reads startData.message and signs it, meaning externally-provided content from a third‑party web service is ingested and directly drives signing/registration actions.

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

• Direct money access detected (high risk: 1.00). The skill is explicitly a blockchain wallet for the Monad chain: it creates and controls wallets, manages MON balances, signs messages (SIWE), and—critically—includes code to send transactions (connectedWallet.sendTransaction({...}) and tx.wait()). It requires and uses private keys and RPC endpoints, i.e., direct crypto wallet and transaction functionality. This is a specific crypto/blockchain execution capability (moving funds), not a generic tool, so it grants direct financial execution authority.