Product guideDocumentation
Open preflight
Product overview

Stop unsafe execution before the wallet signs.

Centaurion is a pre-execution firewall for autonomous wallets. It proves whether an unsigned transaction matches the agent's stated mission and the owner's policy before funds can move.

Input
Intent + unsigned transaction
Decision
ALLOW · WARN · BLOCK
Authorization
60-second Safety Receipt
01

How preflight works

One request crosses four explicit security boundaries.

  1. 01

    Declare the mission

    The agent submits a structured intent, the unsigned EVM transaction, and the wallet owner's policy.

  2. 02

    Decode and simulate

    Centaurion resolves the calldata and simulates the transaction to observe transfers, calls, approvals, and state changes.

  3. 03

    Compare intent with effects

    Deterministic rules check what the agent requested against what the transaction would actually do.

  4. 04

    Enforce before signing

    Unsafe execution is blocked. A matching transaction receives a short-lived, transaction-bound Safety Receipt.

02

What the feature checks

The decision is evidence-backed and deterministic, not a model-generated opinion.

Asset limits

Native value, token outflows, minimum output, and unexpected transfers.

Destinations

Router targets, recipients, spenders, and every contract touched by execution.

Dangerous behavior

Delegatecalls, contract creation, self-destructs, and administrative operations.

Authority changes

Admin events and sensitive proxy storage writes that could transfer control.

Evidence quality

Simulation chain, trace capability, state block, freshness, and revert status.

Transaction binding

Exact calldata, structured intent, policy, effects, signer, expiry, and nonce.

03

Decisions and risk index

Findings determine the verdict first; severity weights produce the display score.

ALLOW8

No findings. A receipt may be issued.

WARN20–79

Review is required before execution.

BLOCK80–98

At least one blocking rule was violated.

low 5 + medium 14 + high 28 + critical 38The score is a severity index, not a probability of loss.
04

What the demo simulates

Both scenarios present the same swap-shaped calldata with very different effects.

Safe routeALLOW
  • Spends exactly 100 USDC
  • Returns 0.035 WETH
  • Sends output to the user wallet
  • Touches only allowlisted contracts
Attack routeBLOCK
  • Drains 1,000 USDC
  • Sends WETH to an attacker
  • Executes a forbidden delegatecall
  • Writes the attacker into the admin slot

The dashboard uses deterministic server fixtures so the demonstration is repeatable. It does not broadcast a transaction or move funds. The production API can be configured with live simulation providers.

05

Safety Receipt

An ALLOW decision is useful only if it cannot be reused for a different transaction.

01SimulateExact transaction
02SignEIP-712 receipt
03VerifyHashes + expiry
04ConsumeNonce used once

The receipt binds chain, sender, target, value, calldata, intent, policy, effects, simulation state, signer, expiry, and nonce. Change one byte and verification fails.

06

Service surface

The console uses fixture endpoints; agents submit real inputs through these services.

POST /v1/inspectFree calldata decoding and advisory warnings.FREE
POST /v1/preflightSimulation, policy enforcement, and Safety Receipt.x402
GET /v1/chainsChain catalog and available simulation evidence.PUBLIC

See the signing boundary in action.

Run both scenarios and compare declared intent with simulated execution.

Open preflight