first-principles

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs the agent to "把【】里的内容换成用户给的真实信息" and to use the template verbatim, which will cause any user-provided secrets (API keys, passwords, tokens) placed in the placeholders to be reproduced in the LLM's output.