design

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

• Third-party content exposure detected (high risk: 0.90). The skill's "External Content And Scraping" section in SKILL.md explicitly instructs the agent to act as a strict 1:1 cloner when "the user provides a URL and the system provides the page content and screenshot," which means the agent will ingest and act on arbitrary public webpage content (untrusted third-party data) as part of its workflow.