privacy-assessment-rails

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

• Third-party content exposure detected (high risk: 0.90). The skill's Assessment Reference (A2b) explicitly requires the agent to "always perform a web search" to discover market-specific PII patterns (public web pages/government docs), which the agent must read and record to drive PII classification and findings, so it ingests untrusted third-party content that can materially change analysis.