t2000-safeguards

Warn

Audited by Snyk on Mar 10, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

  • Direct money access detected (high risk: 1.00). The skill is explicitly about autonomous agent wallet controls and outbound transfers. It defines USDC per-transaction and daily send limits, lists concrete outbound commands ("t2000 send", "t2000 pay — x402 API payments", "sentinel bounties"), and exposes SDK methods (agent.enforcer.set, lock, unlock, getConfig) to configure and control those financial operations. This is a purpose-built financial safeguard/control module tied to sending payments on-chain or via a payment API, not a generic tool — therefore it directly relates to executing and governing financial transactions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 08:18 PM