Skills
skills/dbt-labs/dbt-agent-skills/running-dbt-commands/Gen Agent Trust Hub

running-dbt-commands

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is designed to guide the agent in executing shell commands for the dbt CLI tool, including dbt build, dbt show, dbt list, and dbt run.
  • [DATA_EXPOSURE]: Provides instructions for accessing and analyzing the target/run_results.json file, which contains metadata regarding the execution of data models and tests.
  • [PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection as it processes external execution data.
  • Ingestion points: The agent is instructed to read execution metadata from the target/run_results.json file using tools like cat and jq.
  • Boundary markers: No explicit delimiters or boundary markers are defined to isolate the ingested JSON content from the agent's internal reasoning.
  • Capability inventory: The skill possesses the capability to execute complex shell commands and interact with database environments through the dbt CLI.
  • Sanitization: The skill does not specify sanitization or validation routines for the content of the run_results.json file prior to analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 02:42 PM