wechatide-skill

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The repository documents several high-risk primitives (an API to execute supplied JS in the runtime, tools that can read/set test-account tickets, and cloud-function deploy tools) that enable remote code execution, credential access, and remote code deployment which could be abused for data exfiltration, backdoors, or system compromise.

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

• Third-party content exposure detected (medium risk: 0.30). 该 skill 的运行时会读取并向 LLM 暴露小程序项目内/模拟器产生的自由文本（例如用户可在工作流中触发读取 console/network 命中行作为证据），这些文本来源于被调试应用的运行输出而可被外部输入影响。