databricks-query
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill enables an agent to process external data from Databricks Unity Catalog tables, which creates a surface for potential indirect prompt injection if those tables contain malicious instructions.
- Ingestion points: SQL query results returned from Databricks as described in SKILL.md.
- Boundary markers: Absent; the instructions do not specify the use of delimiters or 'ignore' commands for database content.
- Capability inventory: SQL execution (SELECT, JOIN, CREATE, INSERT) and metadata exploration via the DBSQL MCP server.
- Sanitization: Absent; no specific sanitization steps for database results are outlined in the skill.- [SAFE]: The skill follows security best practices by explicitly instructing the user to use environment variables for the Databricks token and warns against hardcoding credentials in the instructions.
Audit Metadata