no-slop

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill explicitly instructs the editor to "leave verbatim spans intact" (quotes, code, etc.) and to edit user-supplied drafts as-is, which means if a draft contains API keys, tokens, or passwords the model is required to reproduce them verbatim in its output, creating an exfiltration risk.