quant-buddy-skill

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to extract an sk- API key from the user's message and write it into config.json (via replace_string_in_file) and then retry calls, which requires the LLM to handle and embed the secret value in commands/actions—an exfiltration risk.

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

• Third-party content exposure detected (medium risk: 0.30). 运行时路径通过用户问题触发 workflows/**，进而把用户的自由文本 user_query 作为参数传入并被工具执行链读取（如 runMultiFormulaBatchStream.user_query / stockProfile.user_query 等），因此存在间接提示注入的“外部文本被模型摄入/用于工具调用”的风险。