ai-automation-workflows

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

• Third-party content exposure detected (high risk: 0.80). The skill's Pattern 2 "Sequential Pipeline" explicitly runs infsh app run tavily/search-assistant to perform "Research" and stores RESEARCH, which is then passed into a subsequent model prompt to write an article—showing it fetches and ingests likely public web/search results (untrusted third‑party content) that can materially influence downstream actions.