playbook-first-name-cleaning

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

• Third-party content exposure detected (medium risk: 0.30). The workflow ingests per-row outsider-authored free text from user-imported lead fields (first_name_raw, last_name_raw, company_name_raw) and sends them to the LLM agent as the user message in the required runtime step “Node 2 — agent: the locked prompt”.