browser-extension-patterns

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

• Third-party content exposure detected (high risk: 0.70). The skill's content script (content/content-script.js) is explicitly injected into web pages and reads page DOM (document.title, location.href, querySelectorAll) and the background worker calls fetchData(message.url) in response to messages (background/service-worker.js), so it clearly ingests untrusted third‑party web content that could influence subsequent actions.