use-agently

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly instructs the agent to fetch and act on arbitrary public third-party content — e.g., the "Protocols" Web/HTTP commands (use-agently web get ) and Discovery commands (use-agently search / view --uri and use-agently mcp tools/call) which pull marketplace pages, agent descriptions, and external URLs that can influence subsequent tool calls and payments.

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

• Direct money access detected (high risk: 1.00). The skill is explicitly designed to manage crypto payments: it generates an EVM private key (wallet), instructs funding the wallet with USDC on Base, and the CLI "handles wallet management, x402 payments" and exposes commands with --pay to execute payments for MCP, Web/HTTP, and A2A interactions. These are specific crypto/payment operations (wallet creation, on-chain balance, and paid transaction calls), so it grants direct financial execution capability.