The Agent Skills Directory

[SAFE]: The skill is entirely composed of instructional content and documentation regarding Test-Driven Development (TDD) and Ruby on Rails testing. It does not contain any suspicious logic, network exfiltration, or obfuscated content.
[COMMAND_EXECUTION]: The instructions include standard Rails development commands such as bin/rails test and bin/rails db:schema:load. These commands are expected within the context of a development tool and do not involve high-risk patterns like sudo or piping remote content to a shell.
[INDIRECT_PROMPT_INJECTION]: The skill involves processing user-provided code and requirements, which creates a potential surface for indirect prompt injection.
Ingestion points: User-supplied feature descriptions, bug reports, and existing implementation code (referenced in SKILL.md).
Boundary markers: None present in the instructions to separate user data from agent instructions.
Capability inventory: The skill workflow involves creating/modifying files and executing local tests via bin/rails test (referenced in SKILL.md and testing-strategy.md).
Sanitization: No explicit sanitization or validation rules are defined for the data processed during the TDD cycle.
[DYNAMIC_EXECUTION]: The documentation describes the use of standard Rails features like ERB (Embedded Ruby) in YAML fixtures and raw SQL execution via ActiveRecord::Base.connection.execute for migration testing. These are documented as standard practices for the framework and do not constitute an abnormal security risk.

test-driven-development