The Agent Skills Directory

[SAFE]: The skill is composed of purely instructional markdown content and SQL templates. It does not contain any executable scripts, binary files, or installation commands.- [SAFE]: No network operations, external downloads, or remote code execution patterns were found. All references are to internal documentation or official MariaDB knowledge base URLs.- [SAFE]: No hardcoded credentials, sensitive file access, or obfuscation techniques were detected. The skill uses standard MariaDB administrative and diagnostic commands (EXPLAIN, ANALYZE, SHOW INDEX) intended for performace tuning.- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent on how to process user-supplied SQL queries and EXPLAIN output. This represents an ingestion point for untrusted data. However, the risk is negligible as the skill's logic is focused on static analysis and providing recommendations back to the user, with no automated execution of the user-provided content against the host system or network.- [SAFE]: The skill does not attempt to escalate privileges, establish persistence, or hide its intent through metadata poisoning.

mariadb-agents-query-optimizer