design-md

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md’s required runtime workflow fetches Stitch project screen objects and downloads their htmlCode.downloadUrl (HTML/CSS) and screenshot.downloadUrl for analysis, meaning outsider-authored content can be ingested if a project contains user-submitted screens/assets.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs the agent at runtime to fetch and parse external assets via web_fetch/read_url_content from htmlCode.downloadUrl (and optionally screenshot.downloadUrl), and that fetched HTML is parsed to extract design tokens which directly influence generated prompts/output.