data-quality-frameworks
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The documentation references official websites and repositories for Great Expectations, dbt, and Soda. It includes instructions to install the
great_expectationsPython package from the official registry, which is a standard procedure for this framework. - [COMMAND_EXECUTION]: The implementation playbook includes standard shell commands for initializing data quality projects, such as
great_expectations init. These commands are typical for the described workflow and do not exhibit malicious intent. - [DATA_EXFILTRATION]: The Slack notification configuration in the checkpoint YAML file follows security best practices by using the
${SLACK_WEBHOOK}environment variable placeholder instead of hardcoding sensitive credentials. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external datasets for validation. While this represents a data ingestion surface, the provided code templates focus on structural and statistical validation (e.g., uniqueness, null checks, range checks) rather than natural language processing that could be exploited by embedded instructions. The use of structured validation frameworks provides a level of isolation for the agent's logic.
Audit Metadata