The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and refactor existing source code from a Ruby on Rails application. This introduces a surface where instructions hidden within comments or data in the code being refactored could potentially influence the agent's behavior.
Ingestion points: The skill interacts with the host application's files, including services, controllers, and routes in SKILL.md and assets/examples.md.
Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious content embedded in the source files.
Capability inventory: The skill utilizes shell commands such as mkdir, mv, and bundle exec rspec for file manipulation and testing.
Sanitization: There is no documentation of sanitization or validation of the processed code content before interpolation into the agent's workflow.
[COMMAND_EXECUTION]: The skill includes instructions and examples for executing shell commands to facilitate the extraction process.
Evidence: SKILL.md and assets/examples.md contain examples such as mkdir -p my_engine/app/services/my_engine, mv app/services/pricing/calculator.rb ..., and bundle exec rspec spec/services/pricing/. These are standard development tools and are used here within their primary intended purpose for project refactoring.

extract-engine