The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the olares-cli command-line interface to execute various subcommands such as overview and applications. These commands allow the agent to fetch snapshots of CPU, memory, disk, network, and GPU usage metrics.\n- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection via the processing of resource rankings and workload data.\n
Ingestion points: Workload rankings and application resource tables are ingested from olares-cli dashboard applications and overview ranking commands.\n
Boundary markers: The skill does not define specific prompt boundary markers or delimiters for the interpolation of tool output data.\n
Capability inventory: The skill executes vendor-specific CLI commands and includes suite routing to diagnostic skills.\n
Sanitization: The instructions include defensive guidance for the agent, specifically advising it to pin automation and logic to machine-readable fields like kind and raw instead of human-readable display labels to mitigate risks from untrusted content.\n- [DATA_EXFILTRATION]: The skill supports network connectivity probes through the network --test-connectivity command. These operations are part of the intended vendor-provided monitoring functionality to verify internet and IPv6 availability per interface.

olares-dashboard