cournot

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to include a wallet-generated signature inside a base64 PAYMENT-SIGNATURE header (the exact signature value) in outgoing HTTP requests, which requires the LLM/agent to handle and emit a sensitive secret-like value verbatim.

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow ingests outsider-authored free text from the user’s message field in POST {base}/intelligence/v1/resolve and then reuses the same message in POST {base}/intelligence/v1/probability.

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

• Direct money access detected (high risk: 1.00). The skill explicitly implements on-chain payments: it requires an agent wallet/signer, describes x402/b402 payment flows, mandates signing EIP-3009 TransferWithAuthorization, specifies the merchant payTo address, and instructs forming and sending a PAYMENT-SIGNATURE header to complete a paid API call. These are concrete crypto/payment operations (direct financial execution), not generic API or browser actions.