startup-validator

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow explicitly requires performing 10-15+ web searches and "CRITICAL: Use web_fetch to read full articles" from public sources (e.g., Gartner, McKinsey, Statista, Crunchbase, TechCrunch, Product Hunt, GitHub, Stack Overflow) and the references/research_templates.md lists many open/public sites, so the agent will fetch and interpret untrusted third-party web content that can materially influence its analysis and actions.