The Agent Skills Directory

[SAFE]: The skill performs static analysis on local Rails application files to provide performance optimization recommendations. Its operations are restricted to reading configuration (config/database.yml), schema (db/schema.rb), and source code files within the app/ directory.
[SAFE]: The analysis scripts do not perform any network operations or access sensitive system-level files such as SSH keys, AWS credentials, or other environment secrets.
[SAFE]: The provided Ruby scripts use standard libraries and safe parsing methods (such as YAML.safe_load) without employing dynamic code execution (eval or exec) on external or untrusted data.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-controlled project files, representing a surface for indirect prompt injection.
Ingestion points: Reads local project files including config/database.yml, db/schema.rb, and Ruby files in app/controllers, app/models, and app/views.
Boundary markers: No explicit delimiters or warnings are used for the processed content during extraction.
Capability inventory: The skill has read-only access to specific project files and outputs analysis to the console. It lacks network access, file-writing permissions, or dangerous command execution capabilities.
Sanitization: Content is parsed using regex and safe YAML loading, significantly mitigating the risk of malicious payload execution.

postgresql-rails-analyzer