cc-connect-ai-bridge

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow continuously monitors external messaging platforms (Telegram, Feishu, Slack, Discord, DingTalk, WeChat Work, LINE, QQ) where any outsider can send free-text messages to interact with the local AI coding agent.

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 building code from a third-party GitHub repository (chenhg5/cc-connect) and fetching an installation script at runtime via an AI prompt instruction, which constitutes a weak/unknown provenance operational dependency.