snowflake-api

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFE
Full Analysis
  • [Secure Credential Management]: The skill uses environment variables for authentication that are intended to be injected by the execution environment. This avoids hardcoding sensitive credentials and adheres to secure secret management practices.
  • [Targeted Network Communication]: All network operations are directed toward legitimate Snowflake service domains (snowflakecomputing.com). This is consistent with the skill's primary purpose and involves well-known technology endpoints.
  • [Robust Scripting Practices]: The included bash script (snow_query.sh) uses jq to safely construct JSON payloads and parse responses. This prevents common command injection issues that can arise when manipulating data in shell environments.
  • [Standard Utility Dependencies]: The skill relies on common, verifiable system utilities like curl and jq rather than downloading or executing unverifiable external scripts or binaries.
  • [Data Ingestion Consideration]: The skill retrieves results from database queries, which constitutes a data ingestion surface. While the agent should treat external data with caution, this is the intended and necessary functionality for a database integration tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 11:17 PM
Security Audit — agent-trust-hub — snowflake-api