cso

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly requires quoting the exact verbatim code lines that motivated findings (and saving them into reports), and its grep/git checks search for real secret prefixes (sk-, AKIA, ghp_, etc.), which forces the LLM to include actual secret values in its output—an exfiltration risk.