gmgn-narrative

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow uses a pluggable social search interface (X API or Grok API) and fetches arbitrary outsider-authored web pages via a URL fetch interface during verification.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to execute npm install -g gmgn-cli from an unverified public registry if a CLI check fails, constituting a high-tier operational dependency.