deploy-verify

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

• Third-party content exposure detected (high risk: 0.90). The skill's Execution instructions (Primary Health Check using curl and the Console Error Check using browser automation) explicitly fetch and navigate arbitrary production URLs and read page content/console errors from those public sites, which are untrusted third-party content that can materially influence the agent's health verdicts and actions.