dotnet-managedcode-markitdown

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

• Third-party content exposure detected (high risk: 0.70). The skill is about converting “input document” content into Markdown, and at runtime that readable document text would typically come from outside the operating user’s authorship (e.g., uploaded/ingested files), which would then be fed into the LLM context via the Markdown output used downstream.