azure-enclave

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

• Third-party content exposure detected (low risk: 0.10). The required runtime workflow uses the first-party Microsoft Learn documentation URLs (e.g., learn.microsoft.com) via mcp_microsoftdocs:microsoft_docs_fetch/fetch_webpage but does not ingest outsider-authored free text through any attacker-submittable queue/feed.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires fetching remote Markdown documentation at runtime (via mcp_microsoftdocs or fetch_webpage) and lists many learn.microsoft.com pages such as https://learn.microsoft.com/en-us/azure/enclave/troubleshoot which will be injected into the agent context and thus directly influence prompts/responses.