testing-dbt-models
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill employs standard system utilities like
find,grep, andcatalongside thedbtCLI to explore the project structure and run tests. These actions are standard for the intended development workflow and do not pose a security risk. - [INDIRECT_PROMPT_INJECTION]: The skill processes project source files to generate testing configurations. While it reads external content, the risk is minimal as the ingestion is focused on local project metadata for a developer-centric task.
- Ingestion points: Local
schema.ymland.sqlfiles. - Boundary markers: None present.
- Capability inventory: File reads, directory listing, and execution of
dbt test. - Sanitization: None present; relies on agent interpretation of structured data.
- [SAFE]: Analysis of the skill body and metadata reveals no attempts at prompt injection, obfuscation, or unauthorized access to sensitive system resources.
Audit Metadata