tiktok-subscribe

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

• Third-party content exposure detected (medium risk: 0.30). The agent skill monitors TikTok video content, keywords, accounts, and topics via the RedFox API, ingesting titles, descriptions, and user-generated posts where any outsider can author content.

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

• Potentially malicious external URL detected (medium risk: 0.30). The script fetches a client-side JavaScript library from cdn.jsdelivr.net during runtime when rendering reports, which constitutes an operational dependency with reputable unofficial CDN provenance.