weclaw-wechat-ai-bridge

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

• Third-party content exposure detected (medium risk: 0.30). The WeClaw bridge processes inbound WeChat messages from external users and routes them to AI agents, exposing the agent to untrusted outsider-authored chat messages.

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

• Potentially malicious external URL detected (high risk: 0.70). The installation instructions use curl to pipe a remote shell script from GitHub and install a Go package from an unofficial third-party repository, constituting a weak runtime operational dependency.