web-to-markdown

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

• Third-party content exposure detected (low risk: 0.10). The skill fetches arbitrary web pages selected by the user via URL and ingests their content into the agent workflow.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill utilizes remote conversion and proxy services (r.jina.ai and defuddle.md) during runtime execution to fetch and process web content as behavior-selecting routing configuration.