ghost-proxy

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

• Third-party content exposure detected (low risk: 0.10). The skill controls an HTTP proxy that captures and inspects traffic, which can include untrusted web content and responses containing 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 downloading and executing a remote installation script from GitHub via curl during setup, presenting an unverified third-party code execution dependency.