design-qa

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly tells the agent to "use web_fetch to:
• Load the live product/staging site" and asks for "Where can I access it? (URL, staging link, screenshots)," so the agent will fetch and read arbitrary external web pages/URLs (untrusted third‑party content) as part of its review workflow.