Skip to content

Security model

The core question with agentic trading is: if the assistant is wrong — or compromised — how much damage can it do? PrimeDelta is built so the answer is bounded, and the bounds are things you control.

Non-custodial by construction

PrimeDelta never holds your key. Every write is signed by your signer, and the signer is the outer boundary of what's possible:

  • Browser / remote-browser — a human approves every action in a wallet. The assistant can't move anything you don't sign.
  • KMS / raw key — the server signs without prompting. Now the boundary is the caps and gates, not a human.

Choose the weakest signer that does the job; see the signing-modes matrix.

Layers between "the assistant asked" and "funds moved"

  1. Identity gate. Trading requires a KYC-verified, minted DID. An unverified wallet can read but not trade.
  2. Spend caps, enforced off the model. Per-trade and daily dUSD caps are checked before a trade is quoted, so an over-cap request is rejected up front. The model can't reword its way past them.
  3. Opt-in gates. Deposits, withdrawals, brokerage orders, and subaccount actions are off by default. A disabled capability isn't merely discouraged — the tool isn't exposed.
  4. Allowlists. Optionally restrict tradable symbols, native-send recipients, and approval spenders.
  5. Chain-id guard. The RPC's real chain id is checked against the selected network on startup, so a misconfiguration fails fast instead of trading on the wrong chain.
  6. Kill switch. halt() stops all trading immediately (only order cancellation remains).

What a compromised assistant still can't do

  • Sign anything in a browser mode without your wallet approval.
  • Exceed your spend caps.
  • Use a gated capability you didn't enable.
  • Trade a symbol outside your allowlist, if you set one.
  • Move funds on a chain other than the one you configured.

What it can do, within those bounds, is real — so set the bounds deliberately and keep them tight. See Operator hardening.

Remote deployments authenticate callers

A hosted HTTP server authenticates its callers (OAuth or a bearer token) and refuses to start otherwise, and it should sit behind TLS. That's separate from transaction signing — it controls who can reach the tools at all. See Connect Claude web.

Secrets

  • A raw private key and the HTTP auth secret are the sensitive values — keep them out of logs, shell history, and plaintext config. In the plugin, sensitive fields are stored in the OS secret store (Keychain on macOS, Credential Manager on Windows, the Secret Service on Linux) — see Install the plugin.
  • At rest vs at runtime. The secret store protects the key at rest, but at runtime the plugin receives it as a plaintext environment variable, so the running process can read it. That's why a privatekey should be a dedicated, limited-funds wallet, and why KMS is preferred — with KMS the key never leaves the HSM, only signatures come back.
  • A KMS key id/ARN is an identifier, not a secret; the IAM credentials that can use it are what you guard.

Know the edges → Known limitations · Risk & responsible use