iblai-api-apply

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

• Third-party content exposure detected (high risk: 0.70). SKILL.md describes a runtime workflow that fetches application/form data from the organization’s API (e.g., form definitions and applicant/reviewer submission objects), which can include outsider-authored free text such as applicant answers and reviewer decision messages/notes that would be ingested into the agent’s LLM context when the agent renders or summarizes those fields.

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

• Direct money access detected (high risk: 1.00). The skill exposes explicit fee-management endpoints and actions that record and modify monetary transactions: it documents a GET fee history endpoint and a POST /manage//fee endpoint with actions record_payment, waive, refund, and credit (with amount, method, funding_source). Those are specific financial operations (recording payments/refunds/credits) rather than generic APIs, so this grants direct financial execution authority (even though a live payment-processor checkout is noted as not yet wired).