baoyu-url-to-markdown

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and processes arbitrary public URLs (SKILL.md: "Fetch any URL" and references/adapters.md) and includes adapters that parse untrusted, user-generated content from X/Twitter, YouTube, Hacker News and generic pages (see scripts/lib/adapters/* which read page HTML and network JSON payloads), so third-party content is ingested and can materially influence extraction and subsequent agent actions.