The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted project data, which introduces a potential surface for indirect prompt injection.
Ingestion points: The skill reads local project files such as Gemfile, config/application.rb, config/environments/production.rb, config/routes.rb, and generated SAST output like brakeman-report.json.
Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious embedded content within the analyzed files.
Capability inventory: The skill utilizes shell command execution capabilities via bundle to install and run the Brakeman scanner.
Sanitization: There is no evidence of explicit sanitization or filtering of the external content before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill references several external resources for documentation and tools, all of which target well-known and trusted organizations.
Evidence: Links to official Ruby on Rails guides (guides.rubyonrails.org), the Brakeman scanner home page (brakemanscanner.org), the OWASP Cheat Sheet Series, and official GitHub repositories for rubysec, heartcombo, devise-security, and rack.
These references are informational and standard for the domain.

rails-security