app-store-screenshots

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

• Third-party content exposure detected (high risk: 0.80). The skill's workflows (SKILL.md Workflow 1 and Workflow 2) explicitly fetch and scrape open/public third‑party sources—e.g., GET requests to https://itunes.apple.com/search and https://itunes.apple.com/lookup and direct scraping of https://apps.apple.com/us/app/id{appId} HTML for mzstatic.com screenshot URLs—and then parse competitor names, subtitles, screenshots and captions which the agent uses to drive analysis, keyword selection, downloads and downstream actions, so untrusted third‑party content can materially influence behavior.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill's export tool loads and executes remote JavaScript at runtime from the CDN URL https://cdnjs.cloudflare.com/ajax/libs/html2canvas/1.4.1/html2canvas.min.js, which is a required dependency for the browser export flow and therefore constitutes a runtime-executed external dependency.