reverse-browser-automation

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

• Third-party content exposure detected (low risk: 0.10). The skill automates browsers and desktop applications to fetch and interact with arbitrary web pages and applications, making external untrusted web content ingested during runtime a low risk.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill contains instructions and code snippets to clone external repositories via GitHub URLs (such as OpenReverse) during setup, constituting a common unofficial operational dependency.