The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the ccloud command-line interface to retrieve cluster configuration data. This is a legitimate use of the official vendor CLI for administrative verification.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests and processes output from external database queries and CLI commands.
Ingestion points: Results from SQL queries such as SHOW CLUSTER SETTINGS and CLI command output from ccloud cluster info in SKILL.md and references/sql-queries.md.
Boundary markers: None identified; the skill does not use specific delimiters to isolate ingested data from instructions.
Capability inventory: The skill can modify database cluster settings, create new database roles, and grant permissions.
Sanitization: No explicit sanitization or validation of the external output is performed before the agent processes the information.
[SAFE]: All external references and documentation links point to the official cockroachlabs.com domain, which is the verified vendor for this skill. The suggested SQL operations are standard security hardening procedures.

configuring-audit-logging