parallel-workload
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a legitimate technical guide for developers to add new SQL actions and coverage to the Materialize database testing framework. It uses standard Python class structures and provided execution utilities.
- [COMMAND_EXECUTION]: The skill references the use of
bin/mzcompose, which is a project-specific CLI tool used for running tests. This is consistent with the skill's purpose and does not involve arbitrary or malicious command execution. - [DATA_EXFILTRATION]: No network operations or patterns associated with data exfiltration were detected. The
Http.RANDOMparameter mentioned in theexecutemethod is a configuration flag for the database executor, not a general-purpose network request tool. - [PROMPT_INJECTION]: There are no instructions that attempt to bypass AI safety guidelines, override the agent's core instructions, or extract system prompts.
Audit Metadata