azure-blueprints
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill retrieves technical documentation, compliance blueprints, and troubleshooting guides from official Microsoft domains (learn.microsoft.com).
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest documentation from external URLs, which represents a standard but manageable surface for indirect prompt injection.
- Ingestion points: Documentation content fetched from
learn.microsoft.comas described inSKILL.md. - Boundary markers: No explicit delimiters or boundary markers are defined for the fetched content.
- Capability inventory: The skill utilizes
read_file,mcp_microsoftdocs:microsoft_docs_fetch, andfetch_webpagetools. - Sanitization: The skill does not implement specific sanitization or filtering for the retrieved markdown content.
- [SAFE]: The skill includes a version-check mechanism based on
metadata.generated_atto advise the user to update the skill if the content is potentially outdated, which is a best practice for documentation-based skills.
Audit Metadata