programmatic-seo

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs ingesting and grounding generation on third‑party data sources (e.g., Tier 5 "Public / scraped" content and Tier 3 UGC), including guidance like "Pass JSON/CSV rows (tier, source URL, metrics) into prompts", "Use models to structure messy public text into tables", and "Research — ... SEO tools, question databases", which means the agent will read untrusted/open web or user-generated content that can materially influence generation and downstream actions.