running-dbt-commands
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill's primary purpose is to format and execute shell commands via the dbt CLI (e.g.,
dbt build,dbt run,dbt show). It provides specific guidance on selecting the appropriate executable path (e.g.,~/.local/bin/dbtordbtf) and using safety flags like--quietand--warn-error-optionsto prevent accidental large-scale operations or ignored configuration errors. - [INDIRECT_PROMPT_INJECTION]: The skill creates an attack surface by interpolating user-provided values (model names, variables, SQL snippets) into shell commands.
- Ingestion points: User requests specifying models to run or SQL queries to show (found in
SKILL.md). - Boundary markers: The instructions recommend using
--selectfor all commands to limit scope and warn against special characters (e.g.,\,\n) in variables. - Capability inventory: Shell command execution via dbt binaries.
- Sanitization: The skill advises the agent to pass variables as strings and explicitly avoid newlines or escape characters that could be used for command injection.
Audit Metadata