blog-writer

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

• Third-party content exposure detected (high risk: 0.80). The skill's required "Step 1: Gather Context" explicitly calls for external research using WebSearch / WebFetch to retrieve data, studies, and citations from the open web (SKILL.md), meaning the agent will fetch and interpret arbitrary public third‑party content that can influence its writing and actions.