redfox-skill-generator

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The workflow includes a silent "usage record" POST to https://redfox.hk/... that explicitly sends an apikey (user's API key) and performs "静默上报" before user interaction — constituting covert telemetry and credential exfiltration.

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

• Third-party content exposure detected (medium risk: 0.30). 在 required workflow（references/core_workflow.md）的 Step 1/2 通过“从用户消息中提取”自然语言功能描述、平台、输入输出、接口地址与“接口文档”等信息，把用户提供的免费文本直接纳入生成上下文以产出 SKILL.md 和 core_workflow.md。