DocsSecurity model

Security model

W3AI assumes the agent is untrusted and the user is sovereign. Every guarantee follows from this assumption.

Threat model

Malicious agentAn operator runs a poisoned model that attempts unauthorized side-effects.
Compromised operatorOperator keys are stolen and used to sign false receipts.
Hostile websiteA page returns content designed to prompt-inject the agent.
ReplayAn attacker resubmits a previously valid receipt for repeat settlement.
Wallet drainAn agent is tricked into signing a transaction that drains the user.

Sandboxing

Every capsule executes in a WASM sandbox with no ambient capabilities. Network, filesystem, and wallet access are gated by scope tokens minted at intent declaration. The sandbox cannot reach into other capsules, the host browser, or the user's OS.

Defense in depth
Sandboxing alone is necessary but not sufficient. It is paired with simulation, isolation, and economic skin in the game.

Mandatory simulation

No on-chain action is broadcast without first being simulated against a recent snapshot. The user signs a hash of the simulated effects, not the raw transaction bytes. If the broadcast outcome diverges from simulation, the Settlement program rejects the receipt and the operator is slashed.

Effects shown to the user

Balance deltasPer-token before/after for every account touched.
ApprovalsAll token/program approvals being granted.
External callsAny cross-program invocation surfaced explicitly.
Worst-case slippageMEV-aware upper bound, not optimistic estimate.

Wallet isolation

Wallet keys never enter capsule memory. Signing requests are forwarded to a separate signer process which independently re-runs simulation before producing a signature. This holds even when the user opts into unattended execution via a session key.

Slashing

Sim mismatch10% of collateral; receipt voided; user refunded.
Forged receipt100% of collateral; operator removed from Registry.
Scope violation25% of collateral; capability tag revoked.
Liveness failureSoft penalty; reputation score decay.

Disclosure

Responsible disclosure to security@w3ai. A bug bounty pool funded from the treasury rewards proof-of-concept reports proportional to slashable damage avoided.