playbook-word-of-mouth-strategy

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly requires reviewing and monitoring public social media and user-generated content — e.g., "Review comment history on Facebook and Instagram," "monitor brand mentions on Facebook, Instagram, X/Twitter, and TikTok daily," and handling WhatsApp forwards (Sections 4 and Pillar 4/8) — which instructs the agent to ingest untrusted third‑party content that can influence advocacy identification and next actions.