gtm-enrichment-smart

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow ingests outsider-authored free text as the user-supplied email (and optional domain/twitterHandle) and then passes it into multiple merchant API requests (e.g., POST /apollo/people-enrichment, POST /hunter/email-verifier, POST /abstract-company-enrichment/lookup), meaning attacker-controlled free text is consumed without selecting a specific item first.

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

• Direct money access detected (high risk: 1.00). The skill is explicitly a payable payment-recipe: it compiles manifest steps into selat-pay calls, lists per-step prices and per-step maxAmount ceilings, and requires a SELAT_ROUTER/ Circle Gateway funded balance. It describes MPP payments through the SELAT Router, specific POST/GET merchant endpoints with dollar amounts, and CLI commands that execute those selat-pay calls — i.e., it is designed to initiate real monetary transactions. This is direct financial execution capability.