prompt-generator

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt requires reading and verbatim-preserving source files (especially in Convert mode: "preserve ALL content verbatim" and "preserve all code blocks, tables, examples, shell commands exactly as-is"), which forces the LLM to include any embedded secrets (API keys, tokens, passwords) in its generated output, creating an exfiltration risk.