azure-immersive-reader
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation from learn.microsoft.com, which is an official and trusted domain belonging to Microsoft.
- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it processes external documentation.
- Ingestion points: Documentation content is fetched via the mcp_microsoftdocs:microsoft_docs_fetch tool or fetch_webpage from learn.microsoft.com.
- Boundary markers: No explicit markers are defined in the skill instructions to separate external content from the agent's internal reasoning.
- Capability inventory: The skill's capabilities are restricted to information retrieval and documentation fetching; it does not perform command execution, file system modifications, or privileged network operations.
- Sanitization: The risk is significantly reduced because the data source is a trusted and well-known technology vendor domain.
Audit Metadata