NadName Agent

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

• Third-party content exposure detected (low risk: 0.10). The required workflow queries the NNS API (api.nad.domains) to check name availability and get registration payloads, which ingest text from an external web service.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill makes runtime HTTP requests to the third-party domain api.nad.domains for name registration data and availability checks, constituting a common unofficial operational dependency.

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

• Direct money access detected (high risk: 0.70). The skill implements direct blockchain purchases and domain registrations via smart contract calls (registerWithSignature with MON token transfers), making it a direct financial operation. Although private keys/keystores are required to sign transactions, there is no documented independent access control enforced by the service or execution layer (such as external approval gates or multi-sig restrictions beyond local key control/signing).