content-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 explicitly instructs the agent to read existing pages via URLs ("read the existing page (URL via firecrawl/web, or file path)") and to perform SERP analysis using web access ("firecrawl, WebSearch, browse"), which requires fetching and interpreting public third-party web content that can influence writing and action decisions.