Is Turnkey safe to connect to an AI agent?

What an AI agent can do

• Live vs paper: live; official code examples sign on testnets (Dogecoin, Tron, Celestia, Arc, Tempo) source
• Order approval: key infrastructure where keys are only decrypted inside secure enclaves, where the signer and the policy engine run; policies can check value (eth.tx.value) and recipient (eth.tx.to) and set a consensus of users who must approve an action source
• Markets: EVM chains, Solana, Bitcoin, Dogecoin, Tron, Cosmos and other chains
• Pricing: Pay as You Go: 25 free signatures a month, then $0.10 per signature; Pro $99/mo plus $0.05 per signature; Enterprise custom

Safeguards that exist

• Paper, demo or testnet mode: Paper, demo or testnet mode available source
• Withdrawal permission needed or allowed: Agent users are non-root and default-deny; policies can restrict destinations to allowlisted addresses and cap amounts (official docs) source
• Scoped keys, permission scopes or IP whitelisting: Agents get their own API key as a non-root user with zero permissions until policies grant them (official docs) source

Safeguards that are missing

• Can it place live orders unattended?: Can place live orders with no documented approval step source
• Order approval or confirmation options: No approval or limit option in our listing source
• Open source or audited: No public source code in our listing source

Sources

• https://docs.turnkey.com/concepts/policies/overview
• https://docs.turnkey.com/solutions/company-wallets/agentic-wallets

Full listing: Turnkey · How the score works: Safety score method