blog-seo-writer

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

• Third-party content exposure detected (high risk: 1.00). The skill's Workflow 1 ("Análise de Conteúdo dos Concorrentes (se fornecidos)" in SKILL.md) explicitly instructs the agent to analyze competitor URLs provided by the user—public third‑party web pages—which the agent must read and use to shape structure, gaps, CTAs and other decisions, exposing it to untrusted third‑party content that could inject instructions.