scrapling

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow includes fetching and extracting content from user-supplied arbitrary websites (e.g., via the MCP server tools get/fetch/stealthy_fetch parameters and then returning extracted page content strings), so outsider-authored free text from those target pages is ingested into the model/output path.