rails-patterns
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines patterns for ingesting and processing external data which creates a potential surface for indirect prompt injection if the agent uses these patterns to process untrusted content.
- Ingestion points: The
SignupForm(app/forms/signup_form.rb) andinvoice_paramsinInvoicesController(SKILL.md) represent entry points for external data into the application context. - Boundary markers: The code examples demonstrate the use of standard Rails
ActiveModelvalidations and strong parameters as boundaries, though they do not include LLM-specific instructions for handling untrusted text. - Capability inventory: The skill patterns include capabilities for database persistence (
ApplicationRecord.transaction,save!,create!), email dispatch (InvoiceMailer.deliver_later), and background job execution (AccountingExportJob.perform_later). - Sanitization: Input data is sanitized via
ActiveModel::Attributesfor type coercion andvalidatesmacros for format enforcement (e.g.,URI::MailTo::EMAIL_REGEXP).
Audit Metadata