fetch-url

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

• Third-party content exposure detected (low risk: 0.10). The skill fetches arbitrary web pages and URLs chosen at runtime, exposing the agent to outsider-authored free text via web browsing.

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

• Potentially malicious external URL detected (medium risk: 0.30). The script unconditionally makes runtime HTTPS requests to FxTwitter and Jina Reader API endpoints to retrieve content and instructions that govern agent behavior, placing it under common unofficial provenance.