codebase-audit

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt requires the report to include verbatim code snippets and retains original text (代码片段、...保留原文) while also instructing agents to look for hardcoded secrets, so the LLM may be expected to output secret values found in source files without redaction.