The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes standard shell commands (ls, cat, grep, echo) for workflow orchestration and state management. These operations are restricted to project-specific directories like project-specs/ and project-tasks/.
[EXTERNAL_DOWNLOADS]: No external script downloads, remote package installations, or 'curl | bash' patterns were identified. All operations are local or involve spawning internal specialist agents.
[DATA_EXFILTRATION]: There are no network operations or external API calls detected. Data processing is confined to the local project environment.
[CREDENTIALS_UNSAFE]: No hardcoded secrets, API keys, or access to sensitive configuration files (e.g., .ssh, .aws) were found.
[PROMPT_INJECTION]: The skill uses natural instructional language to define its persona and workflow. It does not attempt to bypass safety filters or override core agent instructions.
[REMOTE_CODE_EXECUTION]: The skill manages tasks and spawns other agents but does not execute dynamically generated or untrusted remote code.

agency-orchestrator