startup-validator

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly requires performing "at least 10-15 web searches" and states "CRITICAL: Use web_fetch to read full articles from authoritative sources (Gartner, McKinsey, Statista, Crunchbase...)" and references public sites (Product Hunt, Stack Overflow, TechCrunch), so it fetches and ingests open web content that is untrusted/third-party and the agent must read and interpret it as part of its workflow.