code-simplify

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill requires the agent to read and present "Before" code snippets and detailed plans that include verbatim excerpts of the target code (and to run tests/commands), so if secrets (API keys, tokens, passwords) are present in the code or test outputs the LLM would be asked to include them in its output — creating an exfiltration risk.