gtm-enrichment-deep

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

• Third-party content exposure detected (medium risk: 0.30). The workflow ingests outsider-authored free text (the user-provided email/firstName/lastName/company/domain) at runtime by placing them directly into POST JSON bodies for Apollo/Hunter enrichment endpoints.

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 perform paid API calls that are settled via a payment router. The doc repeatedly states every step is an "MPP on Tempo" payment through the SELAT Router, shows selat-pay CLI commands that compile and execute payment manifests, lists per-step prices and caps, and references settlement via a funded Circle Gateway balance. These are specific payment execution mechanisms (payment endpoints, router, selat-pay), not generic tooling — therefore it grants direct financial execution authority.