x-subscribe

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

• Third-party content exposure detected (medium risk: 0.30). The skill monitors and ingests Twitter/X posts via timeline APIs based on user-subscribed accounts, which process untrusted public social media content containing free text.

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

• Potentially malicious external URL detected (high risk: 0.70). The script fetches client-side assets from external CDNs (jsdelivr) at runtime to render reports, presenting a weak/unknown third-party CDN dependency.