snowpro-study

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a strong anti-hallucination protocol that mandates grounding all generated technical content in official documentation. It prioritizes the Snowflake Documentation Knowledge Extension (Cortex) and falls back to official web sources if unavailable.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute cortex CLI commands for documentation retrieval and agent discovery. This is a standard and expected integration for users within the Snowflake ecosystem.
  • [EXTERNAL_DOWNLOADS]: The skill fetches certification guides and product documentation from official Snowflake domains (docs.snowflake.com and learn.snowflake.com). These are well-known technology service domains and are considered safe sources for the skill's intended educational purpose.
  • [SAFE]: Local file system access is used transparently for performance optimization (caching certification data in ~/.snowflake/...) and persistent progress tracking (saving score history to CSV files in the working directory).
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 03:06 AM
Security Audit — agent-trust-hub — snowpro-study