privacy-assessment-rails

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The workflow reads external web search results during market-specific PII document lookups in Step A2b.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill references an external repository (codeminer42/skills) via npx skills add to install a required dependency skill (privacy-by-design-rails), which provides scripts, rules, and references executed during runtime.