The Agent Skills Directory

[SAFE]: No malicious patterns or suspicious code were identified during the security audit. The skill consists entirely of documentation for a command-line interface.- [COMMAND_EXECUTION]: The skill documents a large set of commands for the csdk CLI, granting the agent capabilities to perform database administration tasks such as managing schemas, tables, permissions, and server-side functions.- [PROMPT_INJECTION]: The skill processes data from external database records (e.g., agent messages, user profiles, audit logs), creating a surface for indirect prompt injection where untrusted data could potentially influence agent behavior.

cli-public