webscraping-ai-automation

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

• Third-party content exposure detected (low risk: 0.10). The required workflow uses Webscraping AI tools to scrape arbitrary web pages selected or provided by the user, exposing the agent to outsider-authored free text via browser extraction.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs configuring an external Model Context Protocol server endpoint at rube.app, which is a third-party/unknown operational dependency failing the dependency gate and provenance standards.