Screening

Every transaction you initiate is scored 0–100 against your behavioral profile before anything executes. Screening runs in a dedicated agent service — the same one that holds the signing key, which is why an unscreened transaction can never be signed. The result is one of three verdicts.

​

The Three Verdicts

​

What Gets Scored

Your profile is built from your past transactions. Each new transaction is checked against:

• Recipient — is this address in your known contacts? Trusted, suspicious, or blocked?
• Amount — is this within your typical range for this recipient? Always in dollars, priced server-side.
• Volume — would this push you over your hourly, daily, or weekly limit?
• Time — is this happening during your active hours and days?
• Token & kind — unfamiliar tokens, unlimited approvals, unknown swap routers, and owner changes all score.

The full signal list with every weight, default limit, and hard guarantee is on the Risk Scoring page.

​

Adjusting Your Limits

Open Settings → Screening limits to see every limit with its default. Editing files a proposal — nothing applies from the app alone. Your agent shows you the exact old → new change on Telegram, and the change takes effect only when you confirm it there (proposals expire after 15 minutes). This is deliberate: Telegram is a different device from your browser, so a compromised web session can’t quietly loosen your own protection. Prefer chat? Asking the agent directly — “raise my daily limit to $50k” — applies immediately; the conversation is the confirmation.

​

Deep Analysis on REVIEW

For every REVIEW-tier transaction, the agent automatically runs external security checks before sending you the Telegram notification:

• GoPlus Security — recipient address reputation, sanctions, phishing, and known scam detection
• Honeypot.is — token security: honeypot detection, mintable supply, buy/sell tax rates

You receive the full report so you can make an informed decision.

​

Responding via Telegram

When a transaction is in REVIEW, you’ll get a Telegram message with:

• Transaction details (recipient, amount, token)
• Risk score and reasons
• Deep analysis results
• [Approve] and [Reject] buttons

Tap Approve to execute, or Reject to block it.

​

Overriding the Agent

The agent advises — it doesn’t gatekeep. In a Protected wallet, every proposal already sits in app.safe.global at 1 of 2 signatures. If the agent flags or blocks something you’re sure about, confirm it there with your backup key and execute — Zhentan syncs the result back automatically.

​

Turning Screening Off

Screening is a choice in Protected wallets:

1. Toggle it off in Settings → Zhentan Guard (or via Telegram).
2. Your transactions now need both of your keys — the agent never signs what it didn’t screen. Each send queues at 1 of 2 and completes when you co-sign with your backup wallet, either in-app (from transaction history) or in the Safe app.

Guarded wallets can’t turn screening off — with one user key against a threshold of two, no second signature could exist. Add a backup key first. Legacy v1 accounts are the exception: their agent co-signs without analysis until they upgrade.

​

Learning Over Time

After every confirmed transaction, Zhentan records the pattern. Recipients you transact with regularly become “known,” amounts normalize, and your screening becomes more accurate over time — with fewer false REVIEW alerts.

​

Telegram Commands

​

If Screening Is Momentarily Unavailable

Screening is fail-closed: if the screening service is ever briefly unreachable, your proposal is accepted and simply waits — you’ll see it as pending with its real signature count (e.g. 1 of 2). Nothing executes without a verdict, and the moment the service returns, screening completes automatically and the normal flow (auto-execute, or the Telegram review) picks up where it left off. Transactions that never involve the agent’s signature — starter wallets and screening-off co-signed transfers — are unaffected and execute as usual. Paused, never unsafe.