The Agent Skills Directory

[COMMAND_EXECUTION]: The skill's core workflow requires the agent to execute shell commands for scaffolding, migrations, and testing (e.g., rails generate, rails db:migrate, bundle exec rspec).
[INDIRECT_PROMPT_INJECTION]: The skill provides an attack surface for indirect prompt injection by using user requirements to determine the scope and content of generated shell commands and application code.
Ingestion points: User-provided descriptions of models, routes, and features used in the workflow.
Boundary markers: None; the skill does not use delimiters or instructions to separate untrusted user input from its own instructions.
Capability inventory: The agent is empowered to execute Rails and Ruby CLI tools via the shell (SKILL.md).
Sanitization: No validation or sanitization is applied to user-provided input before it is used to generate command-line instructions.
[EXTERNAL_DOWNLOADS]: The skill references documentation on a GitHub Pages site (jeffallan.github.io), which is an established hosting platform.
[METADATA_POISONING]: The author URL (https://github.com/Jeffallan) in the metadata does not match the expected vendor name ('neonetz').

rails-expert