bruin-semantic-layer
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a standard workflow for interacting with a local semantic engine tool (
bruin). It operates on local YAML configuration files and database tables within a specified repository structure. - [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and process YAML model files and SQL expressions within the repository's
semantic/directory. - Ingestion points: YAML files (
.yml,.yaml) under thesemantic/directory. - Boundary markers: Not explicitly defined for the file reading process, though instructions are scoped to the repository level.
- Capability inventory: Execution of
bruinCLI commands (validate,check,query) which perform shell-based operations and database queries based on the model definitions. - Sanitization: The documentation explicitly mentions that filter values are SQL-formatted and strings are escaped during SQL generation, which provides a layer of protection against SQL injection within the generated queries.
Audit Metadata