The Agent Skills Directory

[COMMAND_EXECUTION]: The skill leverages standard Rails CLI tools, including bundle exec rspec, bin/rails console, and bin/rails dbconsole. These commands are used as intended for model testing and database management within a development environment.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes application source code that could contain untrusted content.
Ingestion points: Reads files from app/models/, app/validators/, app/services/, app/queries/, and db/schema.rb.
Boundary markers: None identified in the provided instructions.
Capability inventory: Shell command execution via bundle exec and interactive Ruby code execution via bin/rails console.
Sanitization: No sanitization or validation of ingested file content is performed.
[SAFE]: No malicious patterns, obfuscation, or unauthorized data exfiltration attempts were identified. The skill follows best practices for Rails development.

model-agent