nla-create

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly tells the user to supply a private key via command-line arguments (e.g., --private-key <key>), which encourages embedding secret values verbatim in commands and would require the LLM to handle/output secrets directly.

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

• Third-party content exposure detected (high risk: 0.70). The required workflow collects the user’s “Demand” (outsider-authored free text relative to the operating user’s own prompts) via conversational input and encodes it into the LLM context when crafting the demand / arbitration prompt.

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

• Direct money access detected (high risk: 1.00). The skill explicitly implements blockchain escrow creation: it instructs using the nla CLI to lock ERC20 tokens on-chain, requires token amounts and token contract addresses, and shows wallet configuration/private-key options and the nla escrow:create command that performs the on-chain action. This is a specific crypto/blockchain financial execution capability (moving/locking funds and requiring signing), not a generic tool.