fetch-content

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

• Third-party content exposure detected (low risk: 0.10). The skill fetches arbitrary URLs (YouTube, TikTok, tweets, articles, PDFs) provided by the user or extracted from links, which contain outsider-authored free text.

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

• Potentially malicious external URL detected (high risk: 0.70). The script queries api.fxtwitter.com and publish.twitter.com at runtime to fetch tweet content and metadata, presenting an unofficial third-party API dependency with unknown publisher provenance.