supply-chain-automation

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt contains hardcoded API keys, tokens, and plaintext passwords in example configs and uses them directly in headers and SMTP/login calls, which would cause an LLM to handle or output secret values verbatim.

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

• Third-party content exposure detected (high risk: 0.90). The skill's runtime workflows clearly ingest external, untrusted third‑party content—e.g., InvoiceProcessingBot.login_to_portal/download_invoices which scrapes supplier portals (https://portal.supplier.com) and AutomatedReplenishment / SupplyChainAPIIntegration which calls external supplier/ERP/WMS/TMS APIs—then parse that supplier-generated content (invoices, portal pages, API responses) and use it to make decisions and trigger automated actions.