marketing-skills

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and inspect open web content (e.g., "Verifique robots.txt em seudominio.com/robots.txt" and "Teste manualmente suas queries no Perplexity / ChatGPT / Google AI Overviews" in ai-seo.md, plus competitor/app-store scraping and review analysis in ASO and competitor-analysis flows), which are untrusted public sources that the agent must read and whose findings drive actions and recommendations—creating a clear vector for indirect prompt injection.