The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for the agent to run various shell and PowerShell commands to manage the software lifecycle including building, testing, and starting services.
Evidence: Commands such as npm run install:all, npm run build, and node homerail_cli/dist/cli.js start are used throughout the documentation.
[EXTERNAL_DOWNLOADS]: The skill utilizes tools that fetch code and dependencies from external repositories as part of the setup process.
Evidence: The instructions use npm to install packages and git clone to retrieve source code from user-specified local or remote Git addresses.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by processing external data and local repository files.
Ingestion points: Reads target definitions from skills/README.md and configuration from YAML templates such as assets/orchestrations/public-dev-5node.yaml.template.
Boundary markers: Absent; there are no specific delimiting instructions or warnings for the agent to ignore potentially malicious embedded content in these files.
Capability inventory: The skill utilizes capabilities including file system modifications (ln -s, rm, mkdir), external package installation (npm), and containerized service management (node cli.js start, docker).
Sanitization: No explicit validation or escaping of the content read from files is performed before it is processed or used in commands.

homerail-install-ops