tiktok-search

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly states it "Uses the Scrape Creators API via Orthogonal to scrape TikTok data including profiles, hashtags, and trending content," so the agent fetches and ingests user-generated TikTok content (public social media posts/descriptions) which it reads and uses to answer queries, exposing it to potential indirect prompt injection.