vue-creater

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

• Third-party content exposure detected (low risk: 0.10). The workflow allows fetching design tokens from a custom URL or environment variable (TOKEN_URL_LIGHT), which exposes the agent to outsider-authored free text via web retrieval.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill uses weak mirrors and registry URLs (registry.npmmirror.com, npmmirror.com/mirrors/electron/) during setup and configuration, constituting an operational dependency with weak provenance.