tiktok-product-video

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

• Third-party content exposure detected (high risk: 0.85). The skill calls a public-facing NexScope API to fetch TikTok product video records, and those records include outsider-authored free text fields like videoDesc (and potentially hashtags) which are returned by the API and then ingested into the agent’s LLM context when the skill outputs the video table.