azure-synapse-analytics
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and retrieves content from official Microsoft Learn documentation (learn.microsoft.com). These references are used to provide the agent with up-to-date technical information.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external web pages.
- Ingestion points: Numerous documentation URLs under the learn.microsoft.com domain referenced throughout the category tables in SKILL.md.
- Boundary markers: The skill does not implement specific boundary markers or "ignore" instructions for the content it fetches.
- Capability inventory: Uses
mcp_microsoftdocs:microsoft_docs_fetchandfetch_webpageto retrieve content; usesread_fileto access local reference content. - Sanitization: No explicit sanitization or validation of the fetched documentation content is described.
- [SAFE]: No malicious code, prompt injections, or persistence mechanisms were found. All external resources and suggested tools originate from the official vendor (MicrosoftDocs).
Audit Metadata