The Agent Skills Directory

[SAFE]: No security concerns were identified during the analysis of the skill's code and configuration.\n- [COMMAND_EXECUTION]: The skill performs SQL operations using the official Snowflake Python connector. It mitigates SQL injection risks by utilizing parameterized queries for data insertion and a restrictive regular expression (IDENTIFIER_RE) combined with identifier quoting for table names.\n- [DATA_EXFILTRATION]: Network operations are confined to Snowflake's official domains as specified in the metadata's network_egress field. Sensitive credentials are managed through standard environment variables, which is a recommended practice.\n- [PROMPT_INJECTION]: The skill instructions include explicit safety guidelines and usage restrictions that prevent the agent from performing unauthorized operations such as DDL or arbitrary SQL execution.

sink-snowflake-jsonl