distinctive-frontend

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow reads and installs a repository from GitHub, which exposes the agent to outsider-authored free text via GitHub repository content.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs installation of an arbitrary third-party mirror repository via npx skills add, introducing an unverified external code and behavior dependency of high risk.