agentwallet

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

• Third-party content exposure detected (low risk: 0.10). The agent skill accesses arbitrary APIs and searches via x402/fetch where outsider-authored web content or API responses can be ingested.

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

• Direct money access detected (high risk: 1.00). The skill documentation explicitly provides tools and APIs for direct cryptocurrency and token financial execution, including EVM transfers, Solana transfers, EVM/Solana contract calls, and x402/MPP micro-payment signing endpoints designed to move funds and execute on-chain transactions.