inbox

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The workflow monitors an agent inbox via inbox.ts, allowing any outsider to submit free text messages that are subsequently read and processed by the agent.

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

• Direct money access detected (high risk: 1.00). The skill explicitly includes functionality for sending paid messages using crypto/blockchain transactions (sBTC balances, payment flows, wallet signatures, and transactions via x402 payment requirements).