supplier-communication-agent

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

• Third-party content exposure detected (high risk: 0.90). The skill's Step-by-Step Process (section "1. Inbound Message Intake and Classification") explicitly ingests supplier-generated messages across email, supplier portals, EDI, and chat and auto-classifies them to drive automated responses, routing, and escalations, meaning untrusted third‑party content is read and can materially influence agent decisions and tool use.