matlab-connect-databricks-jdbc
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions for legitimate database connectivity and configuration tasks. No malicious patterns, such as obfuscation, unauthorized command execution, or persistence mechanisms, were detected.
- [DATA_EXFILTRATION]: The skill provides guidance on configuring authentication using ".databrickscfg" files, environment variables, and token caching. These are standard, documented methods for managing Databricks credentials and do not represent a security risk when used as instructed.
- [PROMPT_INJECTION]: The skill enables the ingestion of data from Databricks tables into the agent's context. This constitutes a standard attack surface for indirect prompt injection common to database connectivity tools.
- Ingestion points: Data retrieved from external tables via "sqlread" and "fetch" commands in "SKILL.md".
- Boundary markers: None identified in the instructional content.
- Capability inventory: Database write operations via "sqlwrite" and administrative commands via "execute" as described in "SKILL.md".
- Sanitization: Standard database toolbox operations are used; no additional instruction-level sanitization or filtering is mentioned.
Audit Metadata