schema-drift-check
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data that could potentially contain malicious instructions, such as error logs, asset definitions, and warehouse metadata.
- Ingestion points: Error output, asset definitions, rendered queries, and ingestion sync logs as described in SKILL.md.
- Boundary markers: None identified in the skill instructions.
- Capability inventory: The agent is instructed to execute various 'bruin' CLI commands (render, validate, query, cloud) and access the local file system (logs/ directory).
- Sanitization: No specific input sanitization or validation steps are mentioned for the data being analyzed.
- [COMMAND_EXECUTION]: The skill instructions direct the agent to interact with the shell through the 'bruin' CLI utility. It utilizes specific commands such as 'bruin cloud runs diagnose', 'bruin render ', and 'bruin validate ' to perform its primary function of schema diagnosis. These tools are specific to the environment and are used for their intended diagnostic purposes.
Audit Metadata