snowflake-development
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs legitimate static analysis of Snowflake SQL files using a provided Python script. The script uses standard libraries and does not perform network operations, credential access, or dynamic code execution.
- [COMMAND_EXECUTION]: The skill executes a local Python utility
scripts/snowflake_query_helper.py. This script is used for intended developer tasks such as query complexity scoring and warehouse sizing recommendations. - [INDIRECT_PROMPT_INJECTION]: The skill includes functionality to read and analyze user-provided SQL files.
- Ingestion points: Local SQL files read by
snowflake_query_helper.pyvia the--filecommand-line argument. - Boundary markers: None explicitly defined in the file ingestion process to delimit the data from instructions.
- Capability inventory: The tool is limited to local file reading and reporting analysis results to standard output; it does not possess network or high-privilege write capabilities.
- Sanitization: The script uses static regular expression matching to identify SQL anti-patterns; it does not execute the ingested code or directly interpolate the content into LLM prompts.
Audit Metadata