co-design

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads external user feedback via agentation annotations and optional issues, which can contain outsider-authored text.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill references external CDN imports via esm.sh and jsdelivr.net for libraries like Mermaid, React, and Agentation during runtime prototype rendering, but these third-party package delivery networks are common open CDNs without concrete publisher proof, making them a common unofficial operational dependency.