semantic-view-patterns
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: No malicious patterns, data exfiltration mechanisms, or unauthorized privilege escalation attempts were detected. The skill contains SQL scripts and documentation intended for educational purposes regarding Snowflake Semantic Views.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface in 'Apply mode' where the agent processes user-provided SQL definitions. This risk is inherent to the skill's utility and is managed by the agent's platform-level SQL execution constraints.\n- [COMMAND_EXECUTION]: The skill instructs the agent to execute SQL commands on a Snowflake account to deploy tutorial schemas. This is the primary intended functionality of the skill and is explicitly scoped to the user's provided database and schema context.
Audit Metadata