wage-hour-qa

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

• Third-party content exposure detected (high risk: 0.90). The skill's mandatory research workflow (Step 2) instructs the agent to "use your tools (web search, legal research integrations...)" and explicitly permits "search the web — results will be tagged [web search — verify]" and checks web/legal research connectors in the "Research-connector pre-flight," so it fetches and interprets open/public third-party web content that can influence decisions.