synthesis-article-refresh

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

• Third-party content exposure detected (high risk: 0.90). The skill's Quick Start step 1 and "Initial Information Required" explicitly require obtaining a blog post URL and the complete original content (i.e., public/user-generated blog pages), so the agent will ingest untrusted third‑party web content that can materially influence its edits and actions.