treatment-demand-radar

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

• Third-party content exposure detected (high risk: 0.85). At runtime the skill calls UnifAPI endpoints that fetch and return public web/marketplace/social content (e.g., geo/serp generative answers with cited sources and tiktok/hashtags/{id}/videos metadata), which is outsider-authored free text that the agent then places into its LLM context for scoring and reporting.