nebula-scrape-url

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

• Third-party content exposure detected (high risk: 0.90). The skill runs scripts/scrape-page.js on user-supplied URLs to capture screenshots and save page.html from arbitrary public web pages (scraped//page.html), so the agent consumes untrusted, third-party web content as part of its workflow.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill runs the scraper at runtime (node scripts/scrape-page.js https://example.com/pricing) to fetch arbitrary web pages and uses the returned HTML/screenshots as required inputs that are injected into the agent’s context to guide its output, so external pages can directly influence prompts and behavior.