article-writing

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

• Third-party content exposure detected (high risk: 0.70). The skill's "Voice Capture Workflow" explicitly requires collecting and ingesting published articles, newsletters, and X/LinkedIn posts (public social media and other public web content) to extract voice and guide writing, which means untrusted third‑party content would be read and used to influence the agent's outputs and behavior.