tiktok-product-research

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow calls FastMoss’s productSearch API and ingests the returned products fields (e.g., titles, shop/category text, URLs) into the agent’s LLM context; this content is sourced from third-party marketplace/catalog data rather than authored by the operating user, so it is outsider-authored free text.