blog-write

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

• Third-party content exposure detected (high risk: 0.90). The skill's Phase 2 Research explicitly instructs the agent to spawn a "blog-researcher" or run WebSearch to fetch and scrape public web content (e.g., statistics and image URLs from Pixabay/Unsplash/Pexels and arbitrary site search results) which the agent must read, extract, and use to drive citations, charts, images, and writing decisions, creating clear exposure to untrusted third‑party content.