generate-import-html

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests and processes content fetched from external URLs—referenced as cleaned.html, metadata.json, and JSON-LD produced by scrape-webpage/analyze-webpage in SKILL.md's "External Content Safety" and prerequisites—and requires the agent to read and map that untrusted, user/third-party page content into metadata and HTML output, which can materially influence generation decisions and next actions.