The Agent Skills Directory

[COMMAND_EXECUTION]: The skill's primary function is to execute shell commands via the arkcli and jq binaries. These operations are governed by strict safety rules, including the use of a --dry-run flag to preview payloads before execution.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process output from CLI tools, which represents a potential surface for indirect prompt injection. This risk is mitigated by instructions that guide the agent to use the --transform flag for precise data extraction and to follow authentication gates defined in shared skills.
[SAFE]: Implements a mandatory 'Guard Checklist' requiring authentication verification and risk assessment before any action. It also mandates human confirmation for any operations that create, delete, or modify resources.

arkcli-api-explorer