to-markdown

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and converts arbitrary public URLs (see references/fetch.md and the SKILL.md decision tree: trafilatura and Playwright fetch strategies) ingesting untrusted, user-supplied web content that the agent reads and converts into Markdown, which could contain instructions that materially influence downstream actions.