setup-dev-browser

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

• Third-party content exposure detected (low risk: 0.10). The required workflow directs the agent to navigate to arbitrary URLs (such as https://github.com) during setup verification, exposing it to outsider-authored free text.

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 download remote scripts and load remote skills from an arbitrary personal GitHub repository (Melvynx/ai-maxxing-skills), introducing a weak/unknown operational external dependency.