read

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

• Third-party content exposure detected (high risk: 0.75). The required runtime path for /read uses the MCP tools search_pages(query=...) and get_page(page_id=...) to fetch page content/metadata from an external page store (outsider-authored page bodies/fields), which the skill then renders into the LLM context as preview text.