bmad-editorial-review-prose

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly requires outputting "The exact original passage" in the table, so any secrets present in the input (API keys, tokens, passwords, cookies, etc.) would be reproduced verbatim in the LLM's output, creating an exfiltration risk.