tiktok-search

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

• Third-party content exposure detected (medium risk: 0.30). In the “TikTok Search” skill workflow, outsider-authored free text provided by the user (e.g., a requested TikTok handle/hashtag/region) is sent to the Orthogonal Scrape Creators API, which returns scraped TikTok profile/video/hashtag text that the agent can ingest without first selecting a specific trusted item.