microsoft-code-reference

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

• Third-party content exposure detected (high risk: 0.85). The required workflow explicitly fetches “search results, fetched pages, and code samples” at runtime via microsoft_docs_search/microsoft_docs_fetch (and/or mslearn search/fetch), which ingests outsider-authored free text from public Microsoft Learn pages into the agent’s LLM context.