azure-data-share
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches content from official Microsoft documentation (
learn.microsoft.com), which is a well-known and trusted service. - [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for remote documentation. The risk is assessed as safe because the content is sourced from a trusted provider and the skill does not expose dangerous capabilities for processing this data.
- Ingestion points: Remote documentation fetched from
learn.microsoft.comviamcp_microsoftdocs:microsoft_docs_fetchorWebFetch. - Boundary markers: No explicit boundary markers or "ignore instructions" warnings identified in the skill text.
- Capability inventory: The skill does not provide access to subprocesses, file-system writes, or network exfiltration tools.
- Sanitization: Not explicitly present in the skill metadata.
Audit Metadata