azure-databricks
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and fetches documentation from official Microsoft domains. These references are used to provide the agent with current technical guidance and troubleshooting information for Azure Databricks.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external data via documentation fetching tools. While this creates a theoretical attack surface for indirect prompt injection, the risk is mitigated by the use of highly trusted official sources and the informational nature of the content.
- Ingestion points: Data is fetched via
mcp_microsoftdocs:microsoft_docs_fetchorWebFetchfromlearn.microsoft.comas indicated inSKILL.mdand all reference files. - Boundary markers: None explicitly defined in the skill files for the fetched content.
- Capability inventory: The skill contains no subprocess calls, file-write operations, or network exfiltration patterns.
- Sanitization: Content is intended to be processed as markdown documentation.
Audit Metadata