backend-code-review

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly requires quoting "relevant code snippet" and checking for "hardcoded secrets/credentials" in reviewed backend files, which will cause the model to copy secret values verbatim from code into its output unless redaction is enforced—so it creates an exfiltration risk.