ux-expert

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

• Third-party content exposure detected (high risk: 0.80). The skill's "Deep Dive" rules explicitly instruct the agent to fetch and read external "Further Reading" links from law files (e.g., nngroup.com, Medium, Wikipedia and other public websites listed in each law's Further Reading), meaning the agent will retrieve and interpret open/public third‑party content as part of its workflow.