reflect

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt requires reading raw command audit logs and producing data-driven listings and sequences (e.g., most-used commands and command invocations) but gives no instruction to redact sensitive fields, so it could force the LLM to reproduce embedded API keys/tokens/credentials verbatim from those logs.