RateVC

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to "Search using region-appropriate data sources" and lists public/untrusted third-party sources (e.g., LinkedIn, Twitter/X, Crunchbase, SEC EDGAR, IT桔子, 天眼查) as required inputs for scoring and report generation, so the agent will ingest and act on arbitrary public/user-generated content that could carry indirect prompt-injection instructions.