lead-enrichment

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s runtime workflow ingests outsider-provided free text (notably linkedinUrl, plus name/company/domain/email inputs) by POSTing them into third-party enrichment endpoints (e.g., Apollo and Clado) that likely return or process externally authored profile/contact content, meaning the agent is driven by user-supplied values without selecting a specific trusted item first.

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

• Direct money access detected (high risk: 1.00). The skill explicitly compiles each enrichment step into selat-pay calls that are "MPP on Tempo" payments routed through the SELAT Router and "every step settles" — i.e., the skill's workflow performs outbound monetary settlements for each API call. The README even shows selat-pay POST commands for payment-probing and notes per-step caps and settlement configuration. This is a specific, built-in payment execution flow (not generic API/click automation), so it grants direct financial execution authority.