tiktok-keyword-topic-search

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

• Third-party content exposure detected (low risk: 0.10). The required workflow queries the RedFox TikTok API to retrieve topic and work content summaries, which ingest third-party user-generated content from TikTok into the agent context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill makes runtime API calls to redfox.hk (https://redfox.hk/story/api/tiktok/ability/...) which is an arbitrary, unverified third-party service provider, introducing a weak operational dependency.