inbound-lead-triage

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

• Third-party content exposure detected (high risk: 0.75). Outsider free text can enter the agent’s LLM context via the runtime-provided CSV lead exports (e.g., demo.csv:demo_request, trial.csv:trial_signup, content.csv:content_download) whose rows contain outsider-authored fields like name, company, title, and created_at, which are then emitted into queue.json and used downstream by the agent for qualification/enrichment/drafting.