Skip to Content
Agent WalletSafety Rules

Safety Rules

Agent Wallet workflows can read balances, build transactions, and execute swaps. Keep the safety boundary explicit.

Read Versus Write

Request typeExamplesRequired behavior
Read-onlyBalance, receive address, price, trending tokens, history, token infoReturn concise results and one useful next step.
PreparationSwap quote, transaction build, token audit, simulationShow result and risk context; do not submit.
WriteTransfer, swap execute, approval, broadcast, signingAsk for explicit confirmation before execution.
Hardware-gated writeHigh-value transfer, sensitive contract call, hidden-wallet signingRequire OneKey device confirmation and stop if the device rejects.

Never Expose Secrets

Agents must never reveal:

  • Private keys or seed phrases.
  • Decrypted Agent Wallet credentials.
  • Hardware passphrases.
  • Access tokens.
  • Keychain contents or credential payloads.

Confirm Writes

Before any transfer, swap execution, approval, or signing request, show a compact confirmation:

FieldRequired
ActionTransfer, swap, sign, approve, or broadcast
SourceWallet address and chain
DestinationRecipient, contract, or target chain
AmountNative or token amount
FeesGas or fee estimate when available
Risk resultSecurity audit or simulation result when available
Hardware stepDevice confirmation requirement when applicable

Do not submit until the user confirms.

Stop Conditions

Stop and report state when:

  • onekey auth status is unauthenticated.
  • The active address does not match the user’s expected wallet.
  • The device is locked, disconnected, rejected, or waiting for PIN/passphrase.
  • The CLI schema does not expose the parameter the agent wants to use.
  • A security command reports a high-risk result and the user has not explicitly accepted it.
Last updated on