douyin-topic-scraper

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

• Third-party content exposure detected (low risk: 0.10). The agent reads public Douyin topic pages and user posts via browser automation, ingesting outsider-authored social media captions and content.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to automatically download and install a runtime dependency from an external GitHub repository via an unverified third-party landing page, presenting a weak/unknown operational dependency.