scroll-stop-builder

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

• Third-party content exposure detected (high risk: 0.75). The skill ingests outsider-authored free text when the operating user provides an external URL (Option A) and the runtime uses WebFetch to retrieve and extract that page’s copy (public web content) into the agent’s LLM context for customization.

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

• Potentially malicious external URL detected (high risk: 0.70). The optional Card Scanner section includes a runtime script tag that loads and executes remote JavaScript from https://cdnjs.cloudflare.com/ajax/libs/three.js/r128/three.min.js, which is fetched at runtime and required for that feature.