client-onboarding

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

• Third-party content exposure detected (high risk: 1.00). This skill's SKILL.md explicitly requires web search + web fetch for company/competitor research, a linkedin-profile-post-scraper for founder research, and scraping Meta/Google ads and industry scans (Phase 1), and then instructs the agent to read those public third‑party outputs in Phase 2 to drive strategy and execution, so untrusted user-generated/public web content can directly influence decisions and downstream tool chains.