x-article-download

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

• Third-party content exposure detected (low risk: 0.10). The workflow downloads and processes public social media content (X/Twitter tweets, articles, and media) via URLs provided by the user, representing active fetching of external pages rather than monitoring an untrusted outsider feed.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill contains instructions that make HTTP requests to the third-party service r.jina.ai at runtime to parse web content, which constitutes an unverifiable operational dependency with unknown provenance, triggering a high rating.