The Agent Skills Directory

[COMMAND_EXECUTION]: The skill is designed to interact with the local olares-cli binary. It provides structured guidance on using the dashboard subcommand to fetch system performance and status data. These operations are restricted to monitoring and do not involve administrative changes or unsafe shell features.
[DATA_EXFILTRATION]: No patterns of credential harvesting or sensitive file access were detected. The skill focuses on hardware and workload metrics (e.g., CPU, RAM, GPU tasks) which are returned to the agent for user presentation.
[PROMPT_INJECTION]: The instructions do not contain any attempts to override safety filters, bypass system prompts, or induce unrestricted role-play behavior.
[REMOTE_CODE_EXECUTION]: There is no evidence of remote script execution, dynamic code generation, or the use of external package managers. The skill relies entirely on a pre-installed CLI tool on the system PATH.
[EXTERNAL_DOWNLOADS]: The documentation references internal relative paths (e.g., ../olares-shared/SKILL.md) and standard CLI help outputs rather than fetching content from external or untrusted remote servers.

olares-dashboard