The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses revos cubes meta and revos cubes query to interact with the semantic model. These are vendor-provided CLI tools (revosai) used for their intended purpose of data retrieval and metadata discovery.
[EXTERNAL_DOWNLOADS]: No external downloads or remote script executions were detected. All operations use local CLI tools and local file reads (e.g., cubes/*.yml).
[DATA_EXFILTRATION]: While the skill reads sensitive-looking business data (measures, dimensions, revenue), the data is rendered directly in the chat for the user. There are no network operations to non-whitelisted or suspicious domains; data flow remains within the agent-user interaction context.
[PROMPT_INJECTION]: The instructions do not contain attempts to override safety guidelines or bypass agent constraints. It provides structured guidance on how to interpret and execute queries correctly.
[CREDENTIALS_UNSAFE]: No hardcoded credentials, API keys, or secrets were found in the skill file.

query-semantic-model