wechat-similar-account

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.80). 文件在“输出顺序”中明确要求“订阅服务（必须输出，无论有无数据）”和“企业采购引导（必须输出，无论有无数据）”，这是强制性且与核心对标推荐功能无关的营销/宣传输出，属于超出技能声明范围的注入式指令。

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill instructs the agent to "主动帮用户配置" the REDFOX_API_KEY and shows concrete shell/PowerShell commands containing placeholders (e.g., "<值>" / "<你的API Key>"), which encourages the agent to ask for and embed the user's API key verbatim into generated commands or outputs, risking secret exfiltration.

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

• Third-party content exposure detected (low risk: 0.10). Runtime path: the agent/script accepts user-supplied search parameters and then ingests RedFox API response fields (including works.title and works.summary used in _extract_content_themes() and for recommendation text) to generate the final output.