quickstart
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill relies on user-provided input to configure workspace settings and cloud resources. These inputs are used to construct commands executed by the Databricks CLI and local scripts.
- Ingestion points: Information collected from the user includes Databricks workspace URLs, application names, Lakebase project names, and branch names in Step 1, Step 2, and Step 3.
- Boundary markers: The instructions do not implement specific delimiters or safety warnings for the agent to validate user-supplied strings before using them in commands.
- Capability inventory: The collected data is used to populate flags for
uv run quickstartand arguments fordatabricks api getcalls. - Sanitization: There is no explicit instruction to sanitize or verify the format of user-provided URLs or names before they are processed by the shell environment.
- [COMMAND_EXECUTION]: The skill uses the Databricks CLI and a local setup script (
uv run quickstart) to manage authentication profiles and provision cloud resources. While these are privileged operations, they are consistent with the skill's primary function of environment setup for the vendor's platform.
Audit Metadata