data-quality-frameworks

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the great_expectations package using pip. This is a widely recognized and well-known library for data engineering and validation.
  • [DATA_EXFILTRATION]: The implementation templates include a Slack notification action. The provided configuration uses the ${SLACK_WEBHOOK} placeholder, which is a secure practice for managing secrets via environment variables rather than hardcoding credentials.
  • [PROMPT_INJECTION]: Indirect injection surface: The skill implements a data quality pipeline that ingests external dataset values and includes them in generated reports.
  • Ingestion points: Data rows from tables such as 'orders', 'customers', and 'products' as referenced in resources/implementation-playbook.md.
  • Boundary markers: No explicit delimiters are used to wrap the observed data values within the generated markdown report.
  • Capability inventory: The skill uses Python script execution to run validation suites and generates markdown reports based on table content.
  • Sanitization: There is no explicit sanitization logic for the observed_value strings in the report generation code.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 09:45 PM
Security Audit — agent-trust-hub — data-quality-frameworks