google-search

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

• Third-party content exposure detected (medium risk: 0.30). The skill “Google Search API” at https://google.fetcher.sh/api/search performs web searches and ingests the returned Google search results (including snippet/free text from outsider-authored pages) into the agent’s runtime responses.

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

• Direct money access detected (high risk: 1.00). The skill exposes explicit payment-related operations: it documents prepaid API keys/top-up flow and an x402 pay-per-call mode that requires USDC on specific chains and notes automatic signing/transaction retries. It also lists a paid operation named "topup_credits" (an API to add funds). These are specific crypto/payment functions (USDC on Base/Polygon/Arbitrum/Monad/Solana and topup_credits) that enable financial transactions, not merely generic HTTP or browser capabilities.