zynkr-gm

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow reads Google Docs/Sheets such as the ops weekly log and gap-heal trackers which contain or can contain user- and outsider-submitted free text.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill contains a command npx skills add https://github.com/peter-tu-zynkr/zynkr-skill-builder --skill zynkr-gm which fetches and installs code from a remote repository at runtime.