content-brief

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

• Third-party content exposure detected (low risk: 0.10). The workflow reads arbitrary web pages from top-ranking search results and fetches provider documentation via web search/SERP tools.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill requires installing a Model Context Protocol connector from an external third-party domain (get-ryze.ai), representing an unverified operational external dependency with unknown publisher provenance.