building-dbt-semantic-layer

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides documentation and workflows for building dbt Semantic Layer components. It correctly identifies the authoring vendor (dbt Labs) and links to official documentation and repositories.
  • [INDIRECT_PROMPT_INJECTION]: The skill includes explicit instructions to treat project files (SQL, YAML) as untrusted content and to ignore instruction-like text embedded in them, which is a recommended safety practice for agents processing user-controlled files.
  • [EXTERNAL_DOWNLOADS]: The skill mentions the use of official tools like dbt-autofix and dbt-metricflow. All external links point to official dbt Labs domains or repositories, and the tool references are standard for the development ecosystem described.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 08:28 PM
Security Audit — agent-trust-hub — building-dbt-semantic-layer