firebase-local-env-setup

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

• Third-party content exposure detected (high risk: 0.90). The required setup explicitly fetches and installs agent skills and extensions from public third-party sources (e.g., "npx skills add firebase/agent-skills" and "gemini extensions install https://github.com/firebase/agent-skills" in the references), which will cause the agent to load and use untrusted external code that can influence its actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs at runtime to install and run remote agent skills (e.g., "gemini extensions install https://github.com/firebase/agent-skills"), which fetches and installs external code that will be executed and can directly control agent behavior, and this installation is presented as a required dependency.