dbt-unit-tests
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill employs the 'altimate-dbt' CLI and custom tools like 'dbt_unit_test_gen' to facilitate dbt development workflows. The use of shell commands for compilation and local file system access for reading models and writing test configurations is appropriate for the skill's primary function. All identified tools and external CLI references are consistent with the resources belonging to the vendor, 'altimateai'.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection as it processes untrusted SQL code to generate tests.
- Ingestion points: The skill reads model SQL files from the local project directory during the analysis phase.
- Boundary markers: The instructions do not define specific delimiters or instructions to treat the ingested SQL as potentially untrusted data.
- Capability inventory: The agent has access to shell execution via 'bash' and file modification via 'write' and 'edit' tools.
- Sanitization: There is no explicit sanitization step for the ingested SQL code prior to its processing by the analysis and generation tools.
Audit Metadata