seo-content-brief

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to run infsh apps (e.g., "infsh app run tavily/search-assistant" and "infsh app run tavily/extract" with user/provided URLs in the "SERP Analysis Process" and Step 2's extract call) to fetch and analyze top-ranking public web pages, meaning untrusted third‑party content is ingested and used to drive decisions about content structure and actions.