mvp

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

• Third-party content exposure detected (high risk: 0.90). The skill's "WEB APP HANDLING" steps explicitly require "If given a URL, use WebFetch to load the page and analyze its content," so the agent fetches and interprets arbitrary public web pages (untrusted third-party content) as part of its workflow, enabling indirect prompt injection.