sentiment-monitoring

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly requires ingesting and monitoring public, user-generated content—e.g., "brand mentions, comments, and conversations on Xiaohongshu" and web mentions via Google Alerts/third‑party social listening tools—which the agent is expected to read and act on (alerts, escalations, scripted responses), creating clear exposure to untrusted third‑party content.